Integrated Approaches to Monitoring GIAHS Territories:

Requirements, Telematics, Sensorization and

Intelligent Management Solutions

Joel Soares

, Carlos Teixeira

and Ramiro Gonçalves

1,2,3 c

AquaValor-Centro de Valorização e Transferência de Tecnologia da Água-Associação, Rua Doutor Júlio Martins nº1,

5400-342 Chaves, Portugal

Institute for Systems and Computer Engineering, Technology and Science, 4200-465 Porto, Portugal

School of Science and Technology, Universidade de Trás-os-Montes e Alto Douro, 5000-801 Vila Real, Portugal

Keywords: GIAHS, Environmental Monitoring, IoT, Technological Architecture, Sensors.

Abstract: Globally Important Agricultural Heritage Systems (GIAHS) are models of sustainability, as they ensure a

balance between human activity and ecosystem conservation. The Barroso region in Portugal is part of this

network, as it follows traditional natural resource management and resilience practices by local communities.

Given the threats posed by environmental degradation, it is urgent to adopt technological solutions for

monitoring these conditions. Thus, throughout this article, the main threats to the integrity of these territories

will be analyzed, and various methodologies and solutions for environmental monitoring will be presented.

Based on the knowledge acquired, we will present an architecture for a digital solution that includes sensors,

the Internet of Things (IoT), processing units, and platforms for real-time data visualization and alarm

management.

1 INTRODUCTION

The United Nations Food and Agriculture

Organization (FAO) created the Globally Important

Agricultural Heritage Systems (GIAHS) initiative to

identify and protect agricultural systems of

exceptional global value (Koohafkan & Altieri,

2011).

Since the concept originated in 2002, GIAHS

aims to ensure sustainability of dynamic systems

where people and natural environment evolve

together over generations (Arnés García et al., 2020).

In addition to their production function, GIAHS

locations preserve landscapes and agro-biodiversity,

significantly contributing to the development of rural

territories, with a positive balance between field

production and conservation of natural resources

(Agnoletti & Santoro, 2022). They also preserve

intangible cultural values, reinforcing identity and

social cohesion through intergenerational

https://orcid.org/0009-0000-6336-7158

https://orcid.org/0009-0003-2982-5217

https://orcid.org/0000-0001-8698-866X

transmission of knowledge and customs (Nan et al.,

2021). Recently, GIAHS regions have gained global

attention for their resilience and sustainability,

withstanding climate and socio-economic changes

without abandoning ancestral traditions and identities

(Arnés García et al., 2020). Protecting these regions

strengthens regional economic development by

promoting sustainable tourism and consequently

increasing work options for the individuals living in

the area (Jiao et al., 2022). Despite their importance,

GIAHS territories face increasingly complex threats

to their integrity (Figure 1). Climate change, a

mounting threat, increases extreme weather events,

droughts, floods, heatwaves, directly reducing

productivity and degrading ecosystems (Yadav & Jin,

2024). On the contrary, environmental decay, loss of

biodiversity, habitat degradation, and pollution also

threaten GIAHS sites, owing to the over usage of

pesticides and fertilizers causing soil and water

pollution, degrading their quality.

Soares, J., Teixeira, C. and Gonçalves, R.

Integrated Approaches to Monitoring GIAHS Territories: Requirements, Telematics, Sensorization and Intelligent Management Solutions.

DOI: 10.5220/0013894400003982

Paper published under CC license (CC BY-NC-ND 4.0)

In Proceedings of the 22nd International Conference on Informatics in Control, Automation and Robotics (ICINCO 2025) - Volume 2, pages 597-608

ISBN: 978-989-758-770-2; ISSN: 2184-2809

597

At the same time, industrial agriculture and

globalization press GIAHS sites promoting

monoculture and reducing agrobiodiversity,

resilience and sustainability (Agnoletti & Santoro,

2022). Such problems are responsible for eroding the

adaptive capacity, as well as ecological sustainability

of the GIAHS sites.

Despite the need for monitoring, there is no

harmonized framework, and each country defines its

own protocols (Jiao et al., 2022). For this reason,

there can be failures or gaps in the early detection of

variations, which can make decisions for protecting

these sites difficult, making integration with smart

technology and digital monitoring solutions also

relevant (Martins et al., 2022). To fend off this

plague, advanced sensor-based systems with real-

time analysis must be applied for designing more

efficient and adaptive monitoring frameworks

(Morchid et al., 2024). One of the strategies for

minimizing this problem is by using smart, self-

sustaining architectures to enable real-time

monitoring, with the possibility to provide for

automatic alerts for immediate action to be taken in

the occurrence of emerging issues that impact quality

standards.

For such issues to be tackled, an overall

technological and information system design must be

put in place with the capacity for answering the

regions specific requirements. This system must

include advanced environment sensing technology,

smart data handling and processing, as well as

sufficiently backed-up power systems (Mansoor et

al., 2025).

Such requirements are in accordance with the

dynamic conservation concept advocated by FAO,

insofar as in leading the advancement of these regions

not only through preservation, but through the

proactive adaptive extension of GIAHS itself

(Koohafkan & Altieri, 2011).

2 MONITORING

REQUIREMENTS OF GIAHS

TERRITORIES:

2.1 Characteristics GIAHS Territory

GIAHS sites are defined by their agricultural,

cultural, and social diversity, contributing to

environmental sustainability and socioeconomic

resilience (Agnoletti & Santoro, 2022).

Beyond their biodiversity, GIAHS regions

preserve traditional wisdom passed through

generations. This ancestral knowledge includes

cultivation and soil conservation practices that

promote sustainability and rational use of natural

resources (Koohafkan & Altieri, 2011). These

territories feature distinctive landscapes shaped by

long-standing community environment interaction.

These landscapes, in addition to their aesthetic

value, are functional, as they support agricultural

production and contribute to the biodiversity in the

area. Adoption of diversified farming methods makes

it possible for GIAHS to provide communities with

food security, while boosting the local economy with

products of commercial and cultural value (Agnoletti

& Santoro, 2022). Such distinctive features of the

GIAHS enhance socio-economic sustainability, an

added value reinforced through the marketing of

products with a positive impact in addition to

enhancing local tourism with further benefit towards

the continuity of traditional aspects, as well as the

distribution of wealth in the community. For this to

be achieved, it is worth emphasizing the adaptability

these territories harbor, especially regarding climate

change, in addition to environment variability, with

an ability for the local communities to adapt their

farming methods constantly (Lin et al., 2025;

Mekouar, 2023).

These characteristics align with the FAO vision of

vibrant conservation, merging adaptation and

innovation, so GIAHS sites can address present and

future challenges while preserving their heritage

(Koohafkan & Altieri, 2011).

2.2 Indicators for Environmental

Monitoring

The monitoring of a GIAHS location requires specific

strategies, in tune with its peculiarities, as highlighted

above. It requires receiving proper data regarding

soil, air, and water quality (Martins et al., 2022; Jiao

et al., 2022), as can be seen in Figure 1.

Water quality, essential for agriculture and

community well-being, must be monitored for

contaminants caused by agrochemical misuse, which

can pollute water, affect health, and harm biodiversity

(Zia et al., 2013). Conversely, physicochemical

parameters like pH, conductivity, turbidity and

dissolved oxygen also need to be monitored, as these

are crucial quality indicators for everyday usage of

the water. Nonetheless, water availability is also

crucial for territorial sustainability and agriculture

activity (Krklješ et al., 2024). Air quality is a highly

important parameter in GIAHS jurisdictions and an

important barometer for human health. Since there is

an increased level of industrialization and pollution,

TISAS 2025 - Special Session on Trustworthy and Intelligent Smart Agriculture Systems: AI, Blockchain, and IoT Convergence

598

there is an increased demand for regulating the rate of

gases together with suspended particles, which cause

respiratory issues (Borghi et al., 2023).

Figure 1: Integrated environmental indicators and digital

technologies for real-time monitoring in GIAHS territories.

Soil quality is a key factor for the functionality

and longevity of GIAHS sites. For this reason,

systematic monitoring should detect pollutants like

heavy metals and pesticide residues, which are toxic

to ecosystems and human health. A complementary

approach involves monitoring basic nutrients such as

nitrogen, phosphorus, potassium and even organic

matter, key indicators of soil fertility and the

preservation of local balances in the ecosystem

(Rashid et al., 2023).

However, to ensure real-time monitoring, it is also

essential to implement intelligent digital models, such

as wireless sensor networks, the Internet of Things

(IoT), and artificial intelligence (Miller et al., 2025).

This approach allows for the continuous collection of

data on soil nutrients and pollutants, water quality and

availability, pollutant gases concentrations (Musa et

al., 2024), and the presence of suspended particles.

This provides a clear overview of the ecological

condition of the monitored area (Mansoor et al.,

2025).

Incorporating these models within GIAHS sites is

original, since it becomes possible to streamline

environmental control procedures, providing added

value to local products, assisting in fortifying the

resilience of communities faced with external

demands, for example, industrialization and over-use

of toxic agents in agriculture (Martins et al., 2022).

By connecting ancient wisdom with new

technologies, adhering to the percept

on of dynamic

conservation advocated by FAO, a solid and versatile

model can be devised with a perspective that ensures

cultural and ecological integrity preservation of the

GIAHS, assuring a long-term sustainability.

2.3 Key Challenges to Effective

Real-Time Monitoring

Digital ecosystems offer great potential for GIAHS

monitoring but face significant challenges

(Miller et al., 2025).

One of the main challenges is associated with the

enormous technical and architectural complexity of

these systems, since they are integrated systems based

on the IoT, which require a multi-layered with each

layer having a specific function (Maurya et al., 2024).

On the other hand, one of the major challenges of

these systems is closely linked to the management of

large volumes of data (Big Data). The large amounts

of data from the sensors, images from satellites and

meteorological data require acquisition, storage,

processing and analysis processes that are often not

available in this type of territory, due to a lack of

technical capacity, specialized human resources and

limited technological infrastructures. Due to these

challenges, real-time monitoring of this data can often

be compromised, thus interfering with the reliability

and usefulness of the results (Miller et al., 2025).

Regarding the limitations of digital ecosystems,

we highlight the difficulty for merging heterogeneous

data from multiple devices and platforms, since

efficient integration between geographic information

systems, wireless sensor networks and data

management platforms requires the adoption of

standardized protocols (Pan et al., 2023). Another

limitation to consider focuses on the economic

sustainability of these digital systems, often identified

as one of the most critical being also undervalued in

the planning and implementation phases. Maintaining

digital infrastructures, including sensors,

communication networks, data storage and

processing platforms, entails significant operating

costs that can compromise long-term viability,

especially in GIAHS territories located in rural or

remote areas, where technical and financial resources

tend to be more limited (Miller et al., 2025; M. Nawaz

& M. Babar, 2025).

On the other hand, the limited availability of

electrical infrastructure leads to a high dependence on

renewable energy sources, such as solar panels, to

power this type of digital monitoring solution.

However, these methodologies present significant

vulnerabilities, which may reduce system reliability

in adverse conditions (Abdelhamid et al., 2025).

Finally, one of the factors that could be a limitation

for monitoring these territories is the acceptance and

adaptation of local communities. Adopting new

digital technologies requires training and technical

skills, which poses a major challenge considering that

the population is mostly elderly in these communities.

Therefore, measures must, be taken to minimize the

changes caused in local areas, and the population

must be included as a central element of digital

Integrated Approaches to Monitoring GIAHS Territories: Requirements, Telematics, Sensorization and Intelligent Management Solutions

599

ecosystems creating a link between technological

innovation and local knowledge (Zhang et al., 2024).

Although IoT-based digital ecosystems offer a

promising model for real-time monitoring, it is

important to recognize that they have limitations, so

it is crucial to implement solutions that are adapted

and customized to the location of interest.

3 TELEMATICS,

SENSORIZATION AND

INTELLIGENT MANAGEMENT

SOLUTIONS

Effective management of GIAHS territories requires

a precise, sustainable and technologically integrated

approach. Nowadays, there are telematics solutions

on the market offering a range of technological tools

to improve the efficiency and effectiveness of

monitoring and managing these territories, including

high-resolution satellite images, unmanned aerial

vehicles (UAVs) and environmental sensors

deployed on site.

However, the effectiveness of these technologies

increases significantly when integrated into advanced

information management platforms, with data

processing and analysis capabilities, as well as

alarmist capabilities, thus facilitating the early

identification of anomalies or trends (Shar et al.,

2024).

3.1 Satellite Images

Environmental monitoring based on high-resolution

satellite images has developed into a useful

instrument in many scientific and operational

applications in natural resource management,

precision agriculture and natural disaster monitoring

(Sishodia et al., 2020). Such a technique depends on

the frequent scanning of the Earth's surface through

the assistance of satellites equipped with special

sensors. The environment is subsequently

recognized, measured and quantified with a high

degree of spatial and temporal precision (Shar et al.,

2024; Sishodia et al., 2020).

For such a permanent and accurate observation,

satellites such as Sentinel-2, Landsat-8 and

WorlsView-3 are used with spatial resolutions

ranging up to 0.5 meters and with adequate temporal

repetition for the detection of climate change (Drusch

et al., 2012). Such use is particularly beneficial in

areas such as precision agriculture, surveillance of

natural hazards and natural resource management

(Segarra et al., 2020).

The data recording is based on sensors on the

satellites, depending on the type of radiation the

sensors are capable of recording. With regards to

optical sensors, they can capture radiation being

reflected in the near-infrared and the visible range,

performing well in situations where the atmosphere is

still and the conditions clear (Wulder et al., 2016).

Thermal sensors, in contrast, pick up emitted

radiation and can estimate the temperatures at the

surface, while the Synthetic Aperture Radar (SAR)

sensors have the advantage of being independent of

the presence or absence of the light conditions, or fog,

ideal under unfavorable weather (Amitrano et al.,

2021). Accordingly, by the employment of this type

of technology, the evolution in the agricultural

landscapes of GIAHS locations over a period of a few

decades can be examined, and thus accurate

discernment of changes in behavioral attributes in the

land can be identified in a bid to reveal complex and

seasonal dynamics.

However, before an analysis can be conducted on

the images that have been captured, they are required

to go through a pre-processing stage. In this stage,

data will go through the process of radiometric and

atmospheric correction through software such as

Sen2Cor to remove the effect caused by atmospheres

in order to retrieve more accurate surface reflectance

(Main-Knorn et al., 2017). Concurrent with these

atmospheric corrections is the function played by the

radiometric calibration in the quality aspect of the

results. It is typically conducted through the support

of polynomial models whose results have coefficients

of determination greater than 0.88 and root mean

square errors (RMSE) lesser compared to 0.01 (Raut

et al., 2019). With the radiation values properly

corrected, we can now focus on the spatial correction

of the images for them to possess geographical acuity.

Orthorectification ensures accurate spatial correction

with such errors lesser compared to 1 pixel in size. In

addition, technologies such as pan-sharpening fusion

are applied in the improvement of spatial resolution,

particularly in panchromatic and multispectral

sensors as used in WorldView-3 (Park et al., 2020).

Remotely sensed imagery is therefore a valuable

tool in the surveillance of the territory as it has

multiple applications. When in the agricultural area,

they allow for one to monitor the status of the

vegetation, making it possible for the pest to be

identified early, assisting in the assessment of the

water stress and in the making of the decision

regarding fertilization and harvesting (Chattopadhyay

et al., 2024).

TISAS 2025 - Special Session on Trustworthy and Intelligent Smart Agriculture Systems: AI, Blockchain, and IoT Convergence

600

From the environment standpoint, the method has

proven effective in the analysis of illegal

deforestation, assistance in the management of

protected areas and analysis of the impacts of large

infrastructure. Relating to the GIAHS areas, the

utilization of time series of Sentinel-2 and Landsat

imagery has proved extremely effective in the

identification of phenological cycles and the analysis

of the impacts of agricultural and environment

policies.

Among the various associated advantages, global

coverage stands out. However, there are significant

limitations, such as decreased accuracy on cloudy

days and the need for technical resources to process

and interpret the acquired data. With the continuing

development in the methods of artificial intelligence,

it has been made possible to overcome some

shortcomings through the utilization of convulsive

neural networks assisting in the aspect of precision as

well as the aspect of making analysis processes more

automatic (Victor et al., 2024).

3.2 Unmanned Aerial Vehicles (UAVs)

Environmental monitoring by UAVs, also known as

drones, has been a useful tool for the extraction of

high spatial coverage data in a manner that facilitates

observation, description and analysis of ecological

and biophysical characteristics in spatial and

temporal scales difficult to access through the

utilization of other methods (Singh et al., 2024).

UAVs have centimetric imagery offering the

potential for extracting data in ultra-high spatial

resolutions and customized cadences in such a

manner that dynamics in natural habitats can readily

be understood (Singh et al., 2024).

UAVs are multi-purpose platforms equipped with

the latest RGB cameras, multispectral sensors,

hyperspectral sensors and thermal sensors making it

possible to collect images in very high resolutions in

the range from 2 up to 5 cm/pixel depending on the

installed flight altitude and the quality level of the

installed sensor (Cao et al., 2021).

Sensors such as the RedEdge-P whose flight

altitudes range to almost 60 meters offer centimetric

resolution imagery marrying RGB and multispectral

bands such as red and near-infrared. With such

arrangements, it is possible to estimate accurately the

spectral indices such as NDVI (Normalized

Difference Vegetation Index) and NDRE

(Normalized Difference Red Edge) useful for

detecting water stress and vegetation health, with a

specificity equal or superior to ground sensors

(Bhagat et al., 2020; De Castro et al., 2021).

Alongside the above elements, the integration of

thermal cameras in UAVs has been extremely

effective in identifying temperature changes in

vegetation and soil, with the ability to recognize

thermal anomalies with a precision ranging from up

to ±0.1 °C, particularly effective in the early

identification of wildfires or in the delineation of soil

temperature and humidity (Guan et al., 2022). The

non-invasive capability provided by this form of

remote sensing is matched by GNSS (Global

Navigation Satellite System) navigation tools and

also RealTime Kinematic (RTK) differential

correction tools, which provide position precision

levels below 2 cm, making them instrumental in

applications where there is a need for high spatial

precision (Niu et al., 2024). UAVs autonomy and

range depend on the model, with models such as the

DJI Matrice 300 RTK providing flight durations

exceeding 50 minutes and real-time data

communication where the distances go up to 15 km

(Czyża et al., 2023).

Furthermore, various studies emphasize the

potentiality for the use of UAVs in numerous areas of

the environment domain, most notably the efficacy of

this approach in the description of vegetation in

mediterranean crop regions, making it possible for

there to be multi-temporal analysis of land utilization

where there is the possibility of detecting variations

existing in crop dynamics and variations by season

(Yeom et al. 2019). Conversely, UAV utilization in

agricultural environments has been gaining

popularity, most notably given the efficacy with

which this method can monitor agronomic parameters

in real-time. Such systems are increasingly applied in

the early identification of nutritional deficiencies, for

diagnosing water stress and in the identification of

diseases where there can be the implementation of

faster and more accurate measures contributing

towards sustainable precision agriculture (Sharma et

al., 2025).

The advancing development of UAV systems

with increasing autonomy, decreased size and

integration with sensors and machine learning

approaches for automatic analysis of the gathered

data enables new applications towards near-real-time

observation of the environment at lowest operating

costs and maximum flexibility (Tabassum, 2020). In

such a manner, UAVs are receiving a vigorous large-

scale response towards current environmental

concerns with the optimum compromise between

spatial resolution, accessibility and repetition

frequency in the observation (Manjunath & Kumar,

2025).

Integrated Approaches to Monitoring GIAHS Territories: Requirements, Telematics, Sensorization and Intelligent Management Solutions

601

3.3 Sensors Implemented in Situ

Sensors have proven to be effective in monitoring and

managing rural areas, especially natural resources.

Field deployed sensors monitor physical, chemical,

and biological parameters with high temporal and

spatial precision. Using of this type of approach is

worthwhile particularly in remotely located areas

with poor infrastructure where the traditional

methods of monitoring are unsuitable or expensive

(Abdinoor et al., 2025). Accordingly, in the

remainder of this section we will consider some

current solutions for the measurement of air, water

and soil quality.

Meteorological monitoring uses industrial-grade

sensors designed to withstand extreme temperatures,

high humidity or heavy rainfall (Concas et al., 2021).

A representative example of this type of device is the

CWT-BY Outdoor Atmosphere Sensor

(ComWinTop), which brings together, the ability to

collect information such as ambient temperature,

relative humidity, atmospheric pressure, noise levels,

light intensity, particulate matter (PM2.5 and PM10)

and carbon dioxide (CO2) concentration, all in a

single module. This sensor module uses RS485

communication (Modbus RTU), is duly protected by

an IP65 shield and has an accuracy of ±0.3 °C for

temperature and ±2% for humidity accuracy. It is

widely used in agricultural and forestry monitoring

(Concas et al., 2021). Similarly, SenseCap sensors

(Seeed Studio) offer precision, IP66 resistance,

LoRaWAN, and up to 10 years of autonomy, ideal for

remote or low-connectivity locations (González et al.,

2020).

On the other hand, gas concentration monitoring

in rural areas is increasingly important for assessing

air quality. Carbon dioxide (CO₂), ammonia (NH₃),

methane (CH₄), nitrogen dioxide (NO₂), ozone (O₃)

and carbon monoxide (CO) are gases commonly

linked to declining air quality and public concern. In

the search for means of eliminating this pest,

Libelium constitutes a formidable and multi-faced

response in this regard in the sense that it has modular

sensors for the above-mentioned gases and other

gases on the basis of various principles of perception,

namely electrochemical sensors, non-dispersive

infrared (NDIR) and catalytic sensors according to

the nature of the compound to be monitored (Hayat et

al., 2019). The CO₂ NDIR sensor measures up to 5000

ppm and is widely used in greenhouses and compost

facilities for CO₂ accumulation control (Pandey &

Kim, 2007). Electrochemical NH₃ sensors detect

below 5 ppm, ideal for livestock environments where

exposure may harm animal and human health

(Moshayedi et al., 2023).

By integrating these sensors into wireless

communication networks, it is possible to efficiently

monitor large areas, with high autonomy and low

energy impact, promoting the implementation of

sustainable strategies for environmental management

(Concas et al., 2021). Other complementary examples

include the MIPEX-02, a multi-gas sensor that is

suitable for rural and industrial environments, where

its architecture allows to combine the detection of

CO₂ and CH₄ using dual-beam NDIR technology,

guaranteeing reliable measurements, even in adverse

conditions such as excessive dust or high humidity

levels. On the other hand, sensors in the Aeroqual

Series 500 range, which are compatible with various

electrochemical and photoionization detection (PID)

modules, enable mobile data collection in the field

and are suitable for monitoring gas emissions and

assessing air quality in forest areas (Mead et al., 2013;

Whitehill et al., 2022).

Water monitoring is essential for assessing

quality and availability, especially in areas prone to

scarcity or contamination. To assess water

availability, level sensors based on hydrostatic

pressure are used, such as the Liquid Level Sensor

For Water Level (Seed Studio) or the OTT Orpheus

Mini probe, that measure the height of the water

column with high precision (Whitehill et al., 2022).

In addition, these sensors have IP68 protection, ideal

for outdoor water monitoring using pressure

transducers that convert column height into digital

data (Whitehill et al., 2022).

When sites are difficult to access or susceptible to

contamination, ultrasonic or radar sensors can be

implemented, such as the VEGAPULS C 11, that

performs measurements without direct contact (Wu et

al., 2023). About water quality assessment, multi-

parametric sensors such as the YSI EX02 or Proteus

P35 can be implemented, which are made up of

replaceable modules that make it possible to

simultaneously measure pH, electrical conductivity,

dissolved oxygen, turbidity and temperature, among

others, with high precision and resistance to

biofouling (Snazelle, 2015). In addition to these

solutions, Seeed Studio integrates specific and

independent modules for monitoring parameters such

as electrical conductivity, pH, turbidity and water

temperature, developed with the purpose of being

integrated into real-time monitoring systems, making

it possible to remotely and continuously collect

essential data for the characterization and

management of aquatic ecosystems.

TISAS 2025 - Special Session on Trustworthy and Intelligent Smart Agriculture Systems: AI, Blockchain, and IoT Convergence

602

Concerning soil quality, dielectric sensors for

nutrients, such as the Soil NPK Sensor (Renke), are

capable to collect data on the temperature, pH and

electrical conductivity of soils, while also being able

to estimate the concentration of nutrients such as

potassium, phosphorus and nitrogen, all with

response times of less than 1 second. In addition to

these potentialities, it also has an IP68 protection

rating, a decisive factor for its application in open

field agricultural monitoring systems (Afridi et al.,

2022). Another representative sensor is the Teralytic,

capable of measuring pH, humidity, temperature, and

NPK nutrients using LoRa for wireless data

transmission, ideal for sustainable agriculture (Santos

& Armstrong, 2024).

The wide range of sensors available today enables

the development of robust systems that balance

accuracy, sensitivity, durability, wireless integration,

and long-term stability, thus operating reliably in

harsh conditions with minimal human intervention.

Therefore, to meet these needs, it is important to

use local processing units capable of interpreting the

electrical signals generated by the sensors and, thus,

performing basic pre-processing and communication

operations, highlighting microcontrollers as essential

units for these systems. Arduino, a device based on

the ATmega328P microprocessor, is one of the most

widely used, running at 16 MHz with 32 Kb of flash

memory. These features make it ideal for low-

complexity applications (Tukur Balarabe et al.,

2019). The ESP32 is characterized by combining a

240 MHz dual-core CPU with Wi-Fi and Bluetooth

connectivity and a low-power deep-sleep mode (<150

µA), which makes this system suitable for

autonomous systems with low energy requirements

(M. Broell et al., 2023).

The Raspberry Pi series, on the other hand,

represents a more robust and versatile solution,

including models ranging from the Model B (ARM

single-core at 700 MHz, 256 MB RAM) to the

Raspberry Pi 4 and 5, equipped with ARM Cortex-

A72 quad-core processors up to 2.4 GHz, 8 GB RAM

and multiple communication interfaces (USB 3.0,

HDMI, gigabit Ethernet, Wi-Fi, Bluetooth), operating

with a Linux system (Hosny et al., 2023).

In addition, the STM32, ARM Cortex-M

microcontrollers, developed by STMicroelectronics,

stand out for their high energy efficiency, good

communication capacity (up to 72 MHz), multiple

communication channels (USART, SPI, I²C, CAN)

and robustness, being widely used in applications that

require stability and low consumption over long

periods of operation (D. Li et al., 2020).

With the adoption of these devices, it becomes

possible to implement edge computing solutions,

significantly reducing latency periods and the

bandwidth required for data transmission, while

increasing the resilience of these solutions in areas

with limited connectivity (Dallaf, 2025).

But for everything to work, there must be

protocols for the sensors and the control panels to talk

to one another. I²C (Inter-Integrated Circuit) protocol

is often used in compact systems due to its simplicity

and low energy consumption, linking up to 127

devices by means of just two wires, the SDA (Serial

Data Line) and the SCL (Serial Clock Line) lines.

This protocol offers a range of speeds from 100 kbps

(standard mode) up to 3.4 Mbps (high speed mode),

but with limited range of up until about 1 meter. On

the other hand, the SPI (Serial Peripheral Interface), a

substitute protocol with higher data transfer speed (up

until 10 Mbps) and lower latency can also be used in

short-range systems like the previous one.

For applications requiring longer distances, RS-

232 supports point-to-point communication of up to

15 meters at 20Kbps, however, it is sensitive to noise

and does not support multiple devices on the same bus

(Rajkumar, 2025). Alternatively, there is the RS-485

protocol which uses differential signaling, allowing

speeds of up to 10 Mbps and coverage of over 1300

meters with the possibility of connecting up to 32

devices on the same bus (Scientific, n.d. ). Its use in

extensive agricultural networks has proven its

robustness in the distributed collection of

environmental data (water level, temperature, pH)

over several hectares (Mo et al., 2022).

To overcome the limitations regarding the

infrastructure in rural areas or in distant areas, long-

range and low-power communications arise as

leaders. Among these are considered LoRa, ZigBee,

Wi-Fi, GSM/GPRS, NB-IoT, 4G and 5G. The LoRa

(Long Range) stands out by the maximum range up

to 15 km, by the transmission rates from 0.3 and 27

Kbps and by the low level of consumption in the order

of 10 to 30 mW, ideal for remote and self-sustaining

nodes (Duisebekova et al., 2019). On the other hand,

ZigBee has a more limited range in the order of 10 to

100 meters and is suited in mesh architecture, being

advantageous in environments with existing physical

barriers (Fitriawan et al., 2017).

Wi-Fi provides bandwidths of more than 100

Mbps but requires greater energy consumption. On

the other hand, technologies such as GSM/GPRS

guarantee extended coverage, but the associated

disadvantage is the lower data transmission rate, up to

approximately 115 Kpbs (Hammami, 2019).

Regarding NB-IoT, this protocol operates at rates of

Integrated Approaches to Monitoring GIAHS Territories: Requirements, Telematics, Sensorization and Intelligent Management Solutions

603

between 20 and 250 Kbps, with high signal

penetration and energy efficiency (Waseem et al.,

2025).

As for 4G and the emerging 5G, they guarantee

high-speed transmissions of up to 10 Gbps, with low

latency periods of less than 1 ms in the case of 5G,

which is a determining characteristic for integrating

this type of technology into applications that require

real-time transmissions (Agiwal et al., 2016; Polak et

al., 2024).

Finally, one approach that has been shown to be

effective and amenable for integration in applications

based on IoT monitoring has been the MQTT

(Message Queue Telemetry Transport) protocol.

With TCP/IP operation and publish/subscribe

architecture usage, the MQTT protocol is a very

effective solution in applications with limited

bandwidth, varying latency or intermittent

connectivity. As MQTT is compatible with Wi-Fi, 4G

and 5G technologies, along with the availability of

configurable Quality of Service (QoS) and

bidirectional communications, results that the MQTT

protocol is particularly effective in synchronizing

sensors placed in the field with Cloud platforms with

low energy requirements (Shilpa et al., 2022).

3.4 Visualization, Analysis and

Alarming Tools

Visualization, analysis, and alert tools convert raw

data into structured, user-friendly information,

supporting efficient environmental management

(Guerbaoui et al., 2025; Olatomiwa et al., 2023).

These functions are generally integrated into digital

platforms capable of real-time data acquisition,

storage, and analysis with high scalability

(Geldenhuys et al., 2021). In the field of visualization,

platforms like Grafana and ThingsBoard offer

interactive interfaces for intuitive data representation.

Grafana supports dynamic dashboards with multiple

data sources (e.g., InfluxDB, SQL), enabling time

graphs, thematic maps, 3D modeling, and pattern

detection (Singh, 2023). ThingsBoard, on the other

hand, stands out for its object-oriented architecture

and native integration of georeferenced maps,

offering dashboards with alarm rules based on

acquired parameter values (Chen, 2023). For

analytics, Node-RED and InfluxDB stand out. Node-

RED (IBM) is a low-code tool based on visual flows

that facilitates the construction of data pipelines

through configurable nodes. It integrates IoT sensors,

preprocesses data (filtering, aggregation,

transformation) and sends it to time series databases

(Onwuegbuzie et al., 2024). InfluxDB is a database

specialized in the efficient management of time

series, which supports the integration of large

volumes of continuous data, allowing for complex

historical queries, which leads to the identification of

trends, seasonal anomalies as well as the

substantiation of mitigation strategies.

The alarming component complements these

platforms by allowing the definition of alteration

conditions based on static or dynamic limits, duly

coordinated with sending channels such as e-mail,

SMS, webhooks or internal notifications, reducing

the response time to critical events (Filip et al., 2022).

Integration with Node-RED or InfluxDB enables

anomaly detection and predictive logic, improving

failure anticipation and environmental response.

In addition, the Infracontrol Online platform (Icp

- Infraestruturas Control Portugal, Sitowise Group) is

an open cloud SaaS solution focused on the

centralized management of urban infrastructures,

such as street lighting, waste management and road

signs, as well as the integration of real-time measured

values of environmental parameters. It offers auto-

generated alerts and georeferenced tickets for

maintenance teams, plus real-time visualization and

historical data access. It has an open, scalable

architecture, permitting connectivity with IoT sensors

and interoperability with SCADA/PLC systems, to

foster an overall, integrated management of cities'

operations.

Implementation of digital architectures driven by

software like ThingsBoard, Note-Red, InfluxDB and

Grafana has turned out crucial in constructing

environmental monitoring systems, allowing for the

collection, processing and visual representation of

data in real time. Platforms such as Infracontrol offer

robust mechanisms for operational visualization and

alert management, so this platform can be used to

supervise urban and environmental infrastructures,

aiding decision-making and territorial coordination.

4 FUTURE PRESPECTIVES:

PROPOSED TECHNOLOGICAL

ARCHITECTURE AS A

SOLUTION TO GIAHS

MONITORING

One of the modern world's great anxieties, in the face

of phenomena such as climate change, adoption of

industrial agronomy and devastation of the

environment, is the real-time surveillance of GIAHS

regions - as has been stated in this review.

Sophisticated technological systems should be

TISAS 2025 - Special Session on Trustworthy and Intelligent Smart Agriculture Systems: AI, Blockchain, and IoT Convergence

604

implemented to enable these systems to be surveyed

in real time in a permanent, precise and articulated

way (Jiao et al., 2022). However, the adoption of

these intelligent instruments has numerous

constraints, which highlights the need for the design

of a superior digital architecture able to interconnect

two fundamental characteristics: autonomy and

adaptation towards the territory. With this objective

in mind, in this section we propose the adoption of an

intelligent technological architecture, designed to

offer a sound digital surveillance instrument. This

proposal integrates environmental sensing, data

processing, information management and user

interaction components.

This system has been digitized for the collection

and processing in real time of the data to facilitate the

making of the required and strategic decisions as key

factors in the proper management of the natural

resources in GIAHS sites.

A technological architecture was conceived to

remotely monitor a GIAHS site, in the Barroso area,

in intelligent and integrated manner according to a

modular and expandable model represented in Fig. 2.

Figure 2: Technological Architecture Overview.

The system was designed to ensure proper

collection of environmental data through intelligent

processing devices which facilitate the distribution of

the data in real-time to the various users and

management entities.

At the center of the entire system is the

Sensorization Module whose function is the

extraction of desired environmental parameters on the

soil, water, atmosphere and climatic conditions to

accurately estimate the ecological condition of the

area.

The main element in this architecture is the

Control Unit where the flow of data from the sensors

is directed and the entire operation of the sensor

module is carried out. The control unit acts as the

module manager for the data received from the

sensors in such a way the received data is routed

through the Data Collection, Storage and

Transmission module where the data is formatted and

sufficiently set up for local storage and subsequent

transmission in secured mode back in the other

system modules.

Received data is processed and correctly added

into the Information Management Service with the

capability for real-time visualization, generation of

comprehensive graphic reports, and alarm

management. Access Control and Management

Module allows for the definition and management of

the degrees of access with the purpose of preserving

confidentiality and security of the data.

Finally, the User Interface is the central area in

which the system and the different users

communicate at, where there is visualization in real-

time at a detailed level of the data, establishment of

the alerts and reading the reports.

Briefly, the architecture represents a functional

response towards the GIAHS regions observation

difficulties. Beyond simplifying the local

management, it is even transferable for other regions

and show how the technology can offer concrete

assistance in the conservation and the development of

unique agricultural systems all over the world.

5 CONCLUSIONS

There is a requirement for customized digital

architectures for effective monitoring and

conservation of GIAHS sites. The use of real-time

monitoring of environments with advanced

technologies such as sensors, UAVs, and satellite

images has the potential to enhance adaptive

management as well as site resilience. Against this

background, a technological structure for the

development of an intelligent monitoring system for

Barroso region, in Portugal, has been proposed being

capable to integrate sensor networks, edge

computing, data analysis and visualization tools, and

user-focused alert handling systems.

Its biggest advantage is that it is repeatable and

transferable so that it could potentially be applied to

other areas of GIAHS with different realities and

operational demands.

ACKNOWLEDGEMENTS

The authors are grateful to the Fundação “La Caixa”

and FCT for the financial support through Project

“Barroso GIAHS 4.0 - Ecossistema Digital de

Monitorização e Gestão Ambiental do Barroso”,

Integrated Approaches to Monitoring GIAHS Territories: Requirements, Telematics, Sensorization and Intelligent Management Solutions

605

Projeto Piloto Inovador - Programa PROMOVE “O

futuro do Interior”, call 2022. J. Soares and C.

Teixeira acknowledges national public funding

through “Investimento RE-C05-i02 – Missão

Interface N.° 01/C05-i02/2022”, a project supported

under the PRR (www.recuperarportugal.gov.pt), and

financed by the European Union/Next Generation

EU.

REFERENCES

Abdelhamid, M. A., Abdelkader, T. K., Sayed, H. A. A.,

Zhang, Z., Zhao, X., & Atia, M.F. (2025). Design and

evaluation of a solar powered smart irrigation systemfor

sustainable Urban Agriculture. Scientific Reports,

15(1), 11761.

Abdinoor, J. A., Hashim, Z. K., Horváth, B., Zsebő, S.,

Stencinger, D., Hegedüs, G.,Bede, L., Ijaz, A., &

Kulmány, I. M. (2025). Performance of Low-Cost Air

Temperature Sensors and Applied Calibration

Techniques—A Systematic Review. Atmosphere,

16(7), 842.

Afridi, W. A., Akhter, F., Vitoria, I., & Mukhopadhyay, S.

C. (2022). A technology review and field testing of a

soil water quality monitoring system. International

Conference on Sensing Technology, Agiwal, M., Roy,

A., & Saxena, N. (2016). Next Generation 5G Wireless

Networks: A Comprehensive Survey. IEEE

Communications Surveys & Tutorials, 18, 1-1.

Agnoletti, M., & Santoro, A. (2022). Agricultural heritage

systems and agrobiodiversity. Biodiversity and

Conservation, 31.

Amitrano, D., Di Martino, G., Guida, R., Iervolino, P.,

Iodice, A., Papa, M. N., Riccio, D., & Ruello, G.

(2021). Earth Environmental Monitoring Using Multi-

Temporal Synthetic Aperture Radar: A Critical Review

of Selected Applications. Remote Sensing, 13(4), 604.

Arnés García, M., Yagüe, J. L., de Nicolás, V. L., & Díaz-

Puente, J. M. (2020). Characterization of Globally

Important Agricultural Heritage Systems (GIAHS) in

Europe. Sustainability, 12(4), 1611.

A., Igathinathane, C., Bandillo, N., & Flores, P. (2025).

Optimizing integration techniques for UAS and satellite

image data in precision agriculture—a review. Frontiers

in Remote Sensing, 6, 1622884.

Bhagat, V., Kadam, A., & Kumar, S. (2020). Analysis of

Remote Sensing based Vegetation Indices (VIs) for

Unmanned Aerial System (UAS): A Review. Remote

Sensing of Land, 3, 58-73.

Borghi, F., Spinazzé, A., De Nardis, N., Straccini, S.,

Rovelli, S., Fanti, G., Oxoli, D., Cattaneo, A., Cavallo,

D., & Brovelli, M. (2023). Studies on Air Pollution and

Air Quality in Rural and Agricultural Environments: A

Systematic Review. Environments, 10, 208.

Cao, X., Liu, Y., Yu, R., Han, D., & Su, B. (2021). A

Comparison of UAV RGB and Multispectral Imaging

in Phenotyping for Stay Green of Wheat Population.

Remote Sensing, 13(24), 5173.

Chattopadhyay, D., Balachandra, Y., P, A., Dutta, A., Sahu,

T., Panotra, N., G, M., & Charitha, K. (2024). Precision

Agriculture Technologies for Early Detection of Crop

Pests and Diseases. UTTAR PRADESH JOURNAL

OF ZOOLOGY, 15, 328-342.

Chen, K. (2023). An Adaptable IoT Rule Engine

Framework for Dataflow Monitoring and Control

Strategies.

Concas, F., Mineraud, J., Lagerspetz, E., Varjonen, S., Liu,

X., Puolamäki, K., Nurmi, P., & Tarkoma, S. (2021).

Low-cost outdoor air quality monitoring and sensor

calibration: A survey and critical analysis. ACM

Transactions on Sensor Networks (TOSN), 17(2), 1-44.

Czyża, S., Szuniewicz, K., Kowalczyk, K., Dumalski, A.,

Ogrodniczak, M., & Zieleniewicz, Ł. (2023).

Assessment of Accuracy in Unmanned Aerial

Vehicle (UAV) Pose Estimation with the REAL-Time

Kinematic (RTK) Method on the Example of DJI

Matrice 300 RTK. Sensors, 23, 2092.

Dallaf, A. (2025). Edge Computing in IoT Networks:

Enhancing Efficiency, Reducing Latency, and

Improving Scalability. International Journal of Advanced

Network, Monitoring and Controls, 10, 2025.

De Castro, A., Shi, Y., Maja, J. M., & Peña-Barragán, J. M.

(2021). UAVs for Vegetation Monitoring: Overview

and Recent Scientific Contributions. Remote Sensing,

13, 2139.

Drusch, M., Del Bello, U., Carlier, S., Colin, O., Fernandez,

V., Gascon, F., Hoersch, B., Isola, C., Laberinti, P.,

Martimort, P., Meygret, A., Spoto, F., Sy, O.,

Marchese, F., & Bargellini, P. (2012). Sentinel-2:

ESA's Optical High-Resolution Mission for GMES

Operational Services. Remote Sensing of Environment,

120, 25-36.

Duisebekova, K. S., Sarsenova, Z. N., Pyagay, V. T.,

Tuyakova, Z. N., Duzbayev, N. T., Aitmagambetov, A.

Z., & Amanzholova, S. T. (2019). Environmental

monitoring system for analysis of climatic and

ecological changes using LoRa technology.

Proceedings of the 5th International Conf. on

Engineering and MIS,

Filip, I.-D., Iliescu, C.-M., & Pop, F. (2022). Assertive,

Selective, Scalable IoT-Based Warning System.

Sensors, 22(3), 1015.

Fitriawan, H., Susanto, M., Arifin, A. S., Mausa, D., &

Trisanto, A. (2017). ZigBee based wireless sensor

networks and performance analysis in various

environments. 2017 15th international conference on

quality in research (QiR): International symposium on

electrical and computer engineering, Food, &

Agriculture Organization of the United, N. (2009).

Globally Important Agricultural Heritage Systems. FAO.

Geldenhuys, M. K., Will, J., Pfister, B. J., Haug, M.,

Scharmann, A., & Thamsen, L. (2021). Dependable iot

data stream processing for monitoring and control of

urban infrastructures. 2021 IEEE International

Conference on Cloud Engineering (IC2E),(pp.244-

250).IEEE.

TISAS 2025 - Special Session on Trustworthy and Intelligent Smart Agriculture Systems: AI, Blockchain, and IoT Convergence

606

González, E., Casanova-Chafer, J., Romero, A., Vilanova,

X., Mitrovics, J., & Llobet, E. (2020). LoRa Sensor

Network Development for Air Quality Monitoring or

Detecting Gas Leakage Events. Sensors, 20(21), 6225.

Guan, S., Zhu, Z., & Wang, G. (2022). A Review on UAV-

Based Remote Sensing Technologies for Construction

and Civil Applications. Drones, 6(5), 117.

Guerbaoui, M., el Faiz, S., Ed-Dahhak, A., Lachhab, A.,

Benhala, B., Bakziz, Z., Ichou, I., & Selmani, A.

(2025). From Data to Decisions: A Smart IoT and

Cloud Approach to Environmental Monitoring. E3S

Web of Conferences,

Hammami, A. (2019). Smart environment data monitoring.

2019 International Conference on Computer and

Information Sciences (ICCIS).

Hayat, H., Griuiths, T., Brennan, D., Lewis, R. P., Barclay,

M., Weirman, C., Philip, B., & Searle, J. R. (2019). The

State-of-the-Art of Sensors and Environmental

Monitoring Technologies in Buildings. Sensors,

19(17), 3648.

Hosny, K. M., Magdi, A., Salah, A., El-Komy, O., &

Lashin, N. A. (2023). Internet of things applications

using Raspberry-Pi: a survey. International Journal of

Electrical & Computer Engineering (2088-8708), 13(1).

Jiao, W., Yang, X., & Min, Q. (2022). A review of the

progress in globally important agricultural heritage

systems (GIAHS) monitoring. Sustainability, 14(16),

9958.

Koohafkan, P., Altieri, M., & Initiative, G. (2011). A

methodological framework for the dynamic conservation

of agricultural heritage systems. Geneva (Switzerland):

Land and Water Division, The Food and Agriculture

Organization (FAO) of the United Nations, 1-61.

Krklješ, D. B., Kitić, G. V., Petes, C. M., Birgermajer, S.

S., Stanojev, J. D., Bajac, B. M., Panić, M. N., Radonić,

V. M., Brčeski, I. D., & Janković, N. N. (2024).

Multiparameter water quality monitoring system for

continuous monitoring of fresh waters. IEEE Sensors

Journal, 24(7), 11246-11260.

Li, D., Wu, T., Li, X., He, Q., & Cui, Z. (2020). A Wireless

Multisensor Node for Long- Term Environmental

Parameters Monitoring. Journal of Electrical and

Computer Engineering, 2020(1), 8872711.

Li, J., Pei, Y., Zhao, S., Xiao, R., Sang, X., & Zhang, C.

(2020). A Review of Remote Sensing for

Environmental Monitoring in China. Remote Sensing,

12(7), 1130.

Lin, M., Wang, M., Lu, Y., Zhou, G., Shen, W., Yin, J., &

You, J. (2025). Synergizing Conservation and Tourism

Utilization in Agricultural Heritage Sites: A

Comparative Analysis of Economic Resilience in

Wujiang and Longsheng, China. Land, 14(4), 796.

M. Broell, L., Hanshans, C., & Kimmerle, D. (2023). IoT

on an ESP32: Optimization Methods Regarding Battery

Life and Write Speed to an SD-Card. In S.Goundar

(Ed.), Edge Computing - Technology, Management and

Integration. IntechOpen.

Ma, N., Yang, L., Min, Q., Keyu, B., & Wenhua, L. (2021).

The Significance of Traditional Culture for Agricultural

Biodiversity—Experiences from GIAHS. Journal of

Resources and Ecology, 12.

Main-Knorn, M., Pflug, B., Louis, J., Debaecker, V.,

Müller-Wilm, U., & Gascon, F. (2017). Sen2Cor for

Sentinel-2.

Manjunath, & Kumar, A. (2025). The Future of

Autonomous Drones in Environmental Monitoring and

Disaster Management. International Journal of

Scientific Research and Engineering Trends.

Mansoor, S., Iqbal, S., Popescu, S., Kim, S., Chung, Y., &

Baek, J.-H. (2025). Integration of smart sensors and

IOT in precision agriculture: trends, challenges and

future prospectives. Frontiers in Plant Science.

Martins, J., Gonçalves, C., Silva, J., Gonçalves, R., &

Branco, F. (2022). Digital Ecosystem Model for

GIAHS: The Barroso Agro-Sylvo-Pastoral System.

Sustainability, 14(16), 10349.

Maurya, S., Pal, O., & Sarvakar, K. (2024). Layered

Architecture of IoT. In (pp. 164-194).

Mead, M. I., Popoola, O. A. M., Stewart, G. B., Landshou,

P., Calleja, M., Hayes, M., Baldovi, J. J., McLeod, M.

W., Hodgson, T. F., Dicks, J., Lewis, A., Cohen, J.,

Baron, R., Sauell, J. R., & Jones, R. L. (2013). The use

of electrochemical sensors for monitoring urban air

quality in low-cost, high-density networks.

Atmospheric Environment, 70, 186-203.

Mekouar, M. A. (2023). Food and Agriculture Organization

of the United Nations (FAO). Yearbook of International

Environmental Law, 34(1), yvae031.

Miller, T., Mikiciuk, G., Durlik, I., Mikiciuk, M.,

Łobodzińska, A., & Śnieg, M. (2025a). The IoT and AI

in Agriculture: The Time Is Now—A Systematic

Review of Smart Sensing Technologies. Sensors,

25(12), 3583.

Mo, C., Xie, Z., & Wang, J. (2022). [Retracted] Large-Area

Saline-Alkali-Tolerant Rice Growth Environment

Monitoring System Based on LoRa+UAV. Advances in

Materials Science and Engineering, 2022(1), 9003753.

Morchid, A., El Alami, R., Raezah, A. A., & Sabbar, Y.

(2024). Applications of internet of things (IoT) and

sensors technology to increase food security and

agricultural Sustainability: Benefits and challenges.

Ain Shams Engineering Journal, 15(3), 102509.

Moshayedi, A. J., Khan, A., Hu, J., Nawaz, A., & Zhu, J.

(2023). E-Nose-Driven Advancements in Ammonia

Gas Detection: A Comprehensive Review from

Traditional to Cutting-Edge Systems in Indoor to

Outdoor Agriculture. Sustainability, 15.

Musa, P., Sugeru, H., & Wibowo, E. P. (2024). Wireless

Sensor Networks for Precision Agriculture: A Review

of NPK Sensor Implementations. Sensors, 24(1), 51.

Nan, M., Lun, Y., Qingwen, M., Keyu, B., & Wenhua, L.

(2021). The significance of traditional culture for

agricultural biodiversity—Experiences from GIAHS.

Journal of Resources and Ecology, 12(4), 453-461.

Nawaz, M., & Babar, M. I. K. (2025). IoT and AI for smart

agriculture in resource-constrained environments:

challenges, opportunities and solutions. Discover

Internet of Things, 5(1), 24.

Integrated Approaches to Monitoring GIAHS Territories: Requirements, Telematics, Sensorization and Intelligent Management Solutions

607

Niu, Z., Xia, H., Tao, P., & Ke, T. (2024). Accuracy

Assessment of UAV Photogrammetry System with

RTK Measurements for Direct Georeferencing (Vol. X-

1-2024).

Olatomiwa, L., Ambafi, J. G., Dauda, U. S., Longe, O. M.,

Jack, K. E., Ayoade, I. A., Abubakar, I. N., & Sanusi,

A. K. (2023). A Review of Internet of Things-Based

Visualisation Platforms for Tracking Household

Carbon Footprints. Sustainability, 15(20), 15016.

Onwuegbuzie, I., Olowojebutu, A., & Kayode, A. (2024).

Node-RED and IoT Analytics: A Real-Time Data

Processing and Visualization Platform. 1, 1-12.

Pan, Y., Sun, J., Yu, H., Bai, G., Ge, Y., Luck, J., & Awada,

T. (2023). Transforming agriculture with intelligent

data management and insights. 2023 IEEE International

Conference on Big Data (BigData).

Pandey, S. K., & Kim, K.-H. (2007). The Relative

Performance of NDIR-based Sensors in the Near Real-

time Analysis of CO2 in Air. Sensors, 7(9), 1683-1696.

Park, H., Kim, N., Park, S., & Choi, J. (2020). Sharpening

of Worldview-3 Satellite Images by Generating

Optimal High-Spatial-Resolution Images. Applied

Sciences, 10(20), 7313.

Polak, L., Kufa, J., Sotner, R., & Fryza, T. (2024).

Measurement and Analysis of 4G/5G Mobile Signal

Coverage in a Heavy Industry Environment. Sensors,

24(8), 2538.

Rajkumar, P. (2025). Humidity and Temperature

Monitoring System using Raspberry Pi via RS232

Networking. Array, 100464.

Rashid, A., Schutte, B. J., Ulery, A., Deyholos, M. K.,

Sanogo, S., Lehnhou, E. A., & Beck, L. (2023). Heavy

Metal Contamination in Agricultural Soil:

Environmental Pollutants Auecting Crop Health.

Agronomy, 13(6), 1521.

Raut, B., Kaewmanee, M., Angal, A., Xiong, X., & Helder,

D. (2019). Empirical Absolute Calibration Model for

Multiple Pseudo-Invariant Calibration Sites. Remote

Sensing, 11(9), 1105.

Santos, G., & Armstrong, S. D. (2024). Evaluation of

Commercial Soil Probe (Teralytic NPK) Performance

in Field Conditions. ASA, CSSA, SSSA International

Annual Meeting,

Scientific, C. (n.d. ). RS-232 and RS-485: Maximum cable

lengths. Campbell Scientific. Retrieved July 23 from

http://s.campbellsci.com/documents/us/technicalpaper

s/rs232-rs485-max-dist.pdf

Segarra, J., Buchaillot, M. L., Araus, J. L., & Kefauver, S.

C. (2020). Remote Sensing for Precision Agriculture:

Sentinel-2 Improved Features and Applications.

Agronomy, 10(5), 641.

Shar, K., Boboy Singh, H., Kumar, P., Anand, S., & Mishra,

R. (2024). Remote Sensing Applications in Agriculture:

Monitoring and Decision Support. In (pp. 1-12).

Sharma, H., Sidhu, H., & Bhowmik, A. (2025). Remote

Sensing Using Unmanned Aerial Vehicles for Water

Stress Detection: A Review Focusing on Specialty

Crops. Drones, 9(4), 241.

Singh, A. (2023). A Data Visualization Tool- Grafana.

Singh, K. K., Surasinghe, T. D., & Frazier, A. E. (2024).

Systematic review and best practices for drone remote

sensing of invasive plants. Methods in Ecology and

Evolution, 15(6), 998-1015.

Sishodia, R. P., Ray, R. L., & Singh, S. K. (2020).

Applications of Remote Sensing in Precision

Agriculture: A Review. Remote Sensing, 12(19), 3136.

Snazelle, T. T. (2015). Evaluation of Xylem EXO water-

quality sondes and sensors (2331-1258).

Tabassum, L. (2020). Environmental Monitoring Using AI-

Powered Drones.

Tukur Balarabe, A., Sani, A., & Hassan, Z. (2019). An

Arduino UNO Based Environment Monitoring System.

14(2), 4-09.

Shilpa, V., & Vidya, A. (2022). MQTT based secure

transport layer communication for mutual

authentication in IoT network. Global Transitions

Proceedings, 3(1), 60-66.

Victor, B., Nibali, A., & He, Z. (2024). A systematic review

of the use of Deep Learning in Satellite Imagery for

Agriculture. IEEE Journal of Selected Topics in

Applied Earth Observations and Remote Sensing.

Waseem, M., López, A., Carro, P., Losada, M., Richards,

D., & Aziz, A. (2025). Understanding the Potentials of

Narrowband Internet of Things (NB-IoT) Cellular

Technology: Salient Features, Architecture, Smart

Applications and Quality of Service (QoS) Challenges.

IEEE Open Journal of the Communications Society.

Whitehill, A. R., Long, R. W., Urbanski, S., Colón, M.,

Habel, B., & Landis, M. S. (2022). Evaluation of

Cairpol and Aeroqual Air Sensors in Biomass Burning

Plumes. Atmosphere (Basel), 13(6), 1-22.

Wu, Z., Huang, Y., Huang, K., Yan, K., & Chen, H. (2023).

A Review of Non-Contact Water Level Measurement

Based on Computer Vision and Radar Technology.

Water, 15(18), 3233

Wulder, M. A., White, J. C., Loveland, T. R., Woodcock,

C. E., Belward, A. S., Cohen, W. B., Fosnight, E. A.,

Shaw, J., Masek, J. G., & Roy, D. P. (2016). The global

Landsat archive: Status, consolidation, and direction.

Remote Sensing of Environment, 185, 271-283.

Yadav, K., & Jin, J. (2024). Exploring Sustainability

through existing and potential GIAHS (Globally

Important Agricultural Heritage Systems).

Yeom, J., Jung, J., Chang, A., Ashapure, A., Maeda, M.,

Maeda, A., & Landivar, J. (2019b). Comparison of

Vegetation Indices Derived from UAV Data for

Diuerentiation of Tillage Euects in Agriculture. Remote

Sensing, 11(13), 1548.

Zhang, X., Yang, Q., Al Mamun, A., Masukujjaman, M., &

Masud, M. M. (2024). Acceptance of new agricultural

technology among small rural farmers. Humanities and

Social Sciences Communications, 11(1), 1641.

Zia, H., Harris, N. R., Merrett, G. V., Rivers, M., & Coles,

N. (2013). The impact of agricultural activities on water

quality: A case for collaborative catchment- scale

management using integrated wireless sensor networks.

Computers and Electronics in Agriculture, 96, 126-138.

TISAS 2025 - Special Session on Trustworthy and Intelligent Smart Agriculture Systems: AI, Blockchain, and IoT Convergence

608