A Resilient and Scalable IoT‑Driven Precision Agriculture

Framework with Edge Intelligence, Climate Adaptability, and

Farmer‑Centric Optimization

Kunal Dhaku Jadhav

, V. Krithika

, P. Balakrishnan

, G. Sangeetha

Inbarasu M.

and Saurabh Kumar

Lifelong Learning and Extension, University of Mumbai, Maharashtra, India

Department of Computer Science and Engineering, Akshaya College of Engineering and Technology, Kinathukadavu,

Coimbatore 642109, Tamil Nadu, India

Department of Electrical and Electronics Engineering, J.J. College of Engineering and Technology, Tiruchirappalli, Tamil

Nadu, India

Department of Management Studies, Nandha Engineering College, Vaikkalmedu, Erode - 638052, Tamil Nadu, India

Department of CSE, New Prince Shri Bhavani College of Engineering and Technology, Chennai, Tamil Nadu, India

Department of Computer Science, SoS, Noida International University, Greater Noida -203201, Uttar Pradesh, India

Keywords: Precision Agriculture, IoT Sensor Networks, Edge Computing, Smart Farming, Resource Optimization.

Abstract: An emerging trend that is reshaping the development of precision agriculture is the integration of IoT sensor

networks, edge intelligence, and climate-aware computing technologies. In this paper, we propose a

sustainable and scalable IoT-enabled precision agriculture framework that tackles major downsides of the

previous works such as high infrastructure and deployment cost, connectivity, energy inefficiency and limited

farmer centric usability. The proposed model employs inexpensive, energy-aware sensors and edge computing

for real-time processing and offline operations. It enables modular adaptability across crop types, climate-

informed decision support, automated actuation for irrigation and pest management, and blockchain-based

data ownership. A farmer-centered data dash board and multi-lingual interface overcome the technology

barrier, enabling users to make informed decisions. This study proves not only the improved resource use

efficiency and yield prediction accuracy, but also the sustainability through multi-years of field trials and

economic analysis. The system architecture guarantees flexibility, security and interaction and can be

regarded as a new reference mark for future smart farming.

1 INTRODUCTION

Agriculture is the cornerstone of worldwide food

security and is increasingly coming under pressure

due to population increases, climate change, soil

degradation and unsustainable resource utilization.

The traditional agricultural practices that have

worked in the past do not provide all the answers

demanded by a sustainable agriculture today. With

the rise of the digital age upon the rural countryside,

the combination of the Internet of Things (IoT), smart

sensor networks and data-driven technologies is

reshaping how farms are monitored, managed and

refined.

Precision farming is regarded as a practice to fill

the gap between conventional practices and the

demand of sustainable intensification. However,

available IoT-based systems lack viability because of

high cost of deployment, energy limitations, poor

networking facilities in remote locations, and lack of

adaptability across wide varieties of crops and

climes. Furthermore, many existing solutions are

built without taking the end-user (farmer) into

consideration and are complex to interact with, as the

end-users are generally not technically literate.

This work presents a novel smart-farming

framework built upon the IoT paradigm that

combines edge computation, climate-adaptive

analytics, and farmer-centric approach. Leveraging

real-time, low-latency decision-making at the edge,

Jadhav, K. D., Krithika, V., Balakrishnan, P., Sangeetha, G., Inbarasu, M. and Kumar, S.

A Resilient and Scalable IoTâ

SDriven Precision Agriculture Framework with Edge Intelligence, Climate Adaptability, and Farmerâ

SCentric Optimization.

DOI: 10.5220/0013857300004919

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

In Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies (ICRDICCT‘25 2025) - Volume 1, pages

49-55

ISBN: 978-989-758-777-1

and intuitive, multilingual interfaces, the system

gives farmers rich and timely insights without the

need for a constant online connection. It further

features modularity so as to be adaptable to particular

crops, environments and terrain limitations.

This work aims to provide a scalable, ultra-

resilient and secure solution, involving blockchain-

driven traceability, AI-empowered prediction models

and energy-aware hardware. By overcoming the

limitations of previous systems and giving priority to

sustainability and sustainability access, this

framework highly contributes to the technological

empowerment of growers and to sustainable

agriculture.

2 PROBLEM STATEMENT

Although the IoT technologies are gradually

introduced in agriculture, many precision farming

systems lack some fundamentals to ensure their

practical applicability and long-term success. For

instance, constraints such as high investment in

infrastructure, weak support for offline-rich or low-

connected-rich scenarios, low-energy efficiency of

sensor nodes, and poor generality towards various

crops and climates intensify the challenge. In

addition, the lack of user-friendly interfaces and

localized decision-support tools reduce usability for

farmers who are not so technologically skilled.

Existing IoT solutions for agriculture are met with

the challenge of scalable, robust, and smart that not

only maximizes resource utilization and yield, but

provides farmers with real-time climate-aware

insights, local control, and data ownership. The aim

of this work is to face these challenges by building a

farmer-centred edge-enabled precision agriculture

system fit for real field situations and long-term

sustainability.

3 LITERATURE SURVEY

The use of Internet of Things (IoT) sensor networks

has completely restructured traditional farming to

smart farming in agriculture. Several applications of

IoT for monitoring soil moisture, crop health, climatic

variables and pest activity have been reviewed in

many studies, which are facilitating the farmers to

make more precise decisions at right time (Kumar et

al., 2021; Garg et al., 2021). These breakthroughs

have opened up the possibility of smarter farming

systems, yet the issue of scaling in real-world

conditions and farmers’ access still need addressing.

Sharma and Shivandu (2024) highlighted the

integration of AI and IoT in precision farming with

significant enhancements in monitoring and

forecasting of crop yield. However, they also raised

issues relating to usability and the implementation in

resource poor settings. Similarly, Dutta et al. (2025)

also commercially suggested IoT-based soilless

agriculture framework acknowledging challenges,

such as infrastructure cost and network dependency.

Sattar et al. (2025) solved the configuration problem

of wireless sensor networks, but no modular crop

adaptability and user-centred design were targeted.

Research such as Albanese et al. (2021) and

Morchid et al. (2025) was dedicated to pest detection

and field automation support in the context of edge

computing, which offered reduced latency and cloud

dependence solutions. These methodologies,

however, while interesting, most of the time they did

not take into account the integration with the farming

ecosystem (actuation system) and economic viability.

Furthermore, Giménez Pérez et al. (2024) utilized

sensor networks for the supervision of tomato crops,

and did not provide an adaptation to any crop and

environment.

The challenge to connectivity and offline mode

has been observed (Garg et al., 2021; Sharma &

Shivandu, 2024). Although edge processing was

included in some frameworks (Albanese et al., 2021),

most depended on connectivity to the cloud. In

addition, the absence of common protocols and

secure models for data ownership continues to also

be a common consideration in the literature (Morchid

et al., 2025), which further supports the use of trade-

offs when considering blockchain technology and

interoperable IoT communications.

Some papers proposed user dashboards and

mobile apps, but they were not localized and not

simple enough for not technically sophisticated

farmers (Kumar et al., 2021; Sattar et al., 2025). Not

many systems took real-time actuation or feedback-

driven optimization into account which would restrict

the influence of data analytics in direct agricultural

interventions.

In a nutshell, though current research has moved

forwards a lot in IoT and AI applied to agriculture,

there still exist major challenges in how to make the

solution cost-effective, energy-efficient, resilient to

harsh conditions, and integrated with the end users. In

this paper we propose to fill these gaps with a new,

farmer-centric precision farming architecture that

combines edge computing with climate-resilient

analytics and scalable, secure IoT infrastructure.

ICRDICCT‘25 2025 - INTERNATIONAL CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION,

COMMUNICATION, AND COMPUTING TECHNOLOGIES

4 METHODOLOGY

The methodology is based on the specification,

implementation, deploy-ment, and assessment of a

NGIoT, modular, edge-enabled platform for

precision agriculture. The infrastructure features

scale-ability, climate adaptability, energy efficiency

and a user-centered vector-in all to accommodate a

range of farm sizes and deployment environments.

The framework consists of four major layers,

namely the Sensing Layer, Edge Intelligence Layer,

Communication and Control Layer, and User

Interaction and Visualization Layer. All these layers

are very important for automatic and efficient

agriculture operations.

The Sensing Layer: it is composed of

environmental sensors, which are an affordable, and

an energy-efficient sensors that are implemented in

crop fields in order to measure some critical variables

as soil moisture, temperature, humidity, light

intensity, and pH. The sensing grid includes pest

recognition modules based upon image recognition

techniques for an early warning system. We organize

the sensors in a grid with redundant data paths for

fault-tolerant operation in the presence of node

failures. Figure 1 shows the Workflow of the IoT-

Driven Precision Agriculture Framework.

Figure 1: Workflow of the IoT-driven precision agriculture framework.

The architecture for Edge Intelligence Layer runs

on NodeMCU/ESP32 microcontrollers with ARM

based edge processors. Local data processing,

anomaly detection, and real-time analytics are

processed locally, thus reducing reliance on cloud

support. On-terminal crop health prediction and

irrigation scheduling are powered by lean AI models

optimized with TensorFlow Lite. This design

facilitates decisions even with low-connectivity or

while in off-line mode. Table 1 gives the information

about Sensor Configuration and Deployment

Strategy.

Sensor data is sent out over a Communication

Layer in a hybrid protocol stack (LoRaWAN for long

range and Wi-Fi/BLE for local routing). A set of

protocols, namely MQTT and CoAP, are used for the

sake of integration with cloud platforms and external

APIs. Dynamic topology reconfiguration enables the

sensor network to self-heal and reroute data through

a new path, in the event that a node becomes

unavailable or is physically destroyed.

The Control Layer comprises actuator modules

communicatively connected to irrigation pumps,

nutrient delivery devices, and sprayers. According to

the real time analysis, and aationing criteria the

actuators function independently or can be overridden

by the dashboard manually. The decision logic also

responds to external weather information that is

fetched from integrated weather APIs, in real-time.

A Resilient and Scalable IoTâ

SDriven Precision Agriculture Framework with Edge Intelligence, Climate Adaptability, and

Farmerâ

SCentric Optimization

Table 1: Sensor configuration and deployment strategy.

Sensor Type Parameter Measured Range

Deployment

Depth/Height

Communication

Protocol

Soil Moisture

Sensor

Soil water content

(%)

0 -100%

10–15 cm below

surface

LoRaWAN

Temperature

Sensor

Ambient

temperature (°C)

-40 to 80

°C

1.5m above surface Wi-Fi/BLE

Humidity Sensor

Relative humidity

(

)

0–100% 1.5m above surface BLE

Light Sensor Light intensity (lux)

0–100,000

lux

Top canopy level Wi-Fi

Pest Detection

Camera

Insect & disease

spotting

N/A 1.5m above crop Wi-Fi/Edge Processing

Sensor readings, actuation events and system

decisions are recorded using blockchain for an

immutable and secure ledger. This provides

improved traceability, confidence in the system, and

also means farmers can use their history as evidence

for audits or certifications.

User Interaction Layer: in this layer, a multi-

lingual web and mobile dashboard was offered to fit

the local farmer’s specifics. It comes with data

visualizations, alerts, suggestions, and manual

overrides. Farmers can also provide feedback on the

outcomes of crops, which is then used to further tune

system performance via a reinforcement learning

loop.

To demonstrate the viability of the system,

pyrolysis is trialed in a number of heterogeneous

climate regions and agro-ecological zones with crops

varying from rice, tomatoes and wheat. Performance

indicators like water usage, yield per hectare, network

uptime, and farmer satisfaction are gathered for three

seasons. The reliability, cost-effective efficiency and

environmental impact of the system is evaluated

based on the analysed data.

By this modular and layered approach, the

proposed methodology aims towards both technical

resilience and real-world usability, thereby providing

the ground work for future intelligent, scalable

agricultural systems.

5 RESULTS AND DISCUSSION

Accomplishments The adopted IoT-based precision

agriculture framework was tested in three pilot

testbeds, located in different agro-climatic zones,

with different soil conditions, irrigation patterns, and

crops. The evaluation aimed at assessing how the

system performs on important aspects such as energy

efficiency, ressource control, connectivity reliability,

usability, yield enhancement. The performance

showed great superiority over traditional agriculture

and reported systems.

5.1 System Performance and Network

Resilience

The implemented deployment consisted of more

than 150 sensor nodes equipped with

microcontrollers with edge capabilities in a mesh

topology. Across three growing seasons, the network

achieved an average uptime of 98.2%, despite

exposure to harsh weather conditions. The adaptive

routing protocol provided dynamic reconfiguration of

the sensor data paths to replace lost nodes and to

maintain data flow. The enhanced system robustness,

as demonstrated on the communication loss ratio that

was 34% less compared to a static topology, indicated

the successfulness of our methodology compared to

the state-of-the-art static one.

5.2 Edge Computing and Offline

Functionality

One of the highlights of this work is the application

of edge computing to facilitate the real-time

processing and actuation without the need for

consistent cloud connection. In rural areas with poor

network coverage, it was important for the system to

be run autonomously. During the testing period, 96%

of irrigation decisions were issued directly from the

edge layer, leading to notable reductions in latency

and greater crop responsiveness. By comparison,

traditional cloud-based systems had a delay of up to

7–15 minutes for the same operations, a lag that

weakened crop health particularly during droughts.

ICRDICCT‘25 2025 - INTERNATIONAL CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION,

COMMUNICATION, AND COMPUTING TECHNOLOGIES

Table 2 gives the Edge vs. Cloud-Based Decision

Comparison.

Table 2: Edge vs. cloud-based decision comparison.

Feature

Edge

Computing

Model

Cloud-Based

Model

Decision

Latency

< 1 second 7–15 seconds

Connectivity

Dependency

Low High

Power

Consumption

Low (solar-

assisted)

Moderate to

High

Real-Time

Actuation

Supported Delayed

Offline

Functionality

Yes No

5.3 Resource Optimization and

Environmental Impact

Based on sensor-based irrigation scheduling water

use was reduced by 41%. Soil moisture control

sensor systems and evapotranspiration data

controlled the on/off of actuator systems avoiding

over-irrigation. It also used nutrient level sensors and

precision mapping for fertilizer management. These

resource efficiency measures resulted in an overall

28% reduction in input costs and improved the

sustainability of the farming enterprise. Table 3 gives

the Resource Optimization Outcomes.

Table 3: Resource optimization outcomes.

Crop

Type

Water

Saved

(%)

Fertilizer

Saved

(%)

Yield

Improvement

(%)

Rice 42% 27% 16%

Tomatoes 38% 30% 19%

Wheat 41% 25% 15%

Figure 2: Water usage before and after IoT implementation.

Figure 2 illustrates the bar chart of Water Usage

Before and After IoT Implementation.

5.4 Crop Yield and Quality

Improvements

The framework helped to achieve average yield

increases of 17% over the three crops evaluated in the

study – rice, tomatoes, and wheat – with significant

enhancements in crop uniformity and health. Disease

epidemics were averted by the pest detection modules

and the AI plant health classifiers, allowing timely

interventions. The smart plots had healthier-looking

foliage, faster grain fill rates, and less variation in

crop size and quality, in contrast to control plots,

which were managed with manual monitoring.

5.5 User-Centric Dashboard and

Farmer Engagement

The farmer-oriented interface, designed with

multilingual support and icon-based navigation,

proved to be highly effective. A post-harvest survey

revealed that 88% of participating farmers were able

to independently interpret insights and manage

system recommendations with minimal technical

training. This feedback loop mechanism, where

farmers could review, validate, or adjust system

recommendations, also served to improve the

machine learning model through continual learning.

Table 4 gives the information about the usability

feedback from farmers.

A Resilient and Scalable IoTâ

SDriven Precision Agriculture Framework with Edge Intelligence, Climate Adaptability, and

Farmerâ

SCentric Optimization

Table 4: Usability feedback from farmers.

Evaluation Criteria

Positive Responses

(%)

Ease of Use (Dashboard) 88%

Language Accessibility 90%

Trust in

Recommendations

84%

Willin

ness to Reuse 92%

5.6 Data Security and Traceability via

Blockchain

All sensor data and actuation records were logged on

a lightweight blockchain system. This ensured

tamper-proof documentation and full traceability for

certification and audit purposes. Farmers appreciated

the transparent data ownership, as it gave them better

control and assurance over their farm records. Unlike

many centralized systems that obscure data

governance, this framework fostered trust and long-

term usability.

5.7 Comparative Analysis with

Existing Models

When benchmarked against existing IoT-based

agricultural platforms, the proposed framework

outperformed in multiple domains. Most notably, it

combined multiple technologies IoT, edge

computing, AI, and blockchain into a unified and

operational model. Previous systems were often

limited to monitoring or analytics, whereas our

solution delivered end-to-end automation and

optimization. Moreover, energy efficiency was

improved by 26% through the use of adaptive sleep-

wake cycles and solar-charged sensor nodes. Table 5

gives the Comparative Analysis with Existing

Frameworks.

Table 5: Comparative analysis with existing frameworks.

Feature/Aspect

Proposed

Framewor

Existing IoT

Systems

Offline

Functionalit

Yes No

Climate

Ada

tabilit

Integrated Limited

Edge AI Support Yes Rare

Blockchain

Traceabilit

Included

Not

Supporte

Farmer-Centric UI Multilingual Basic/None

5.8 Challenges and Future Scope

While the results are promising, certain challenges

were encountered. Hardware maintenance in remote

areas required periodic technician visits, and the pest

recognition module showed occasional false positives

in dense canopy conditions. These limitations

highlight areas for future work, such as integrating

drone-based remote diagnostics and developing self-

diagnostic sensor units. Scalability across vastly

different topographies and large farm holdings also

warrants further research to refine network density

and data fusion algorithms.

In conclusion, the proposed framework

successfully bridges the gap between advanced IoT

technology and grassroots agricultural needs. By

addressing known drawbacks such as connectivity

issues, poor usability, and lack of intelligent

actuation, this system sets a new benchmark for

precision agriculture solutions. The synergy between

real-time edge intelligence, environmental

adaptability, and farmer engagement is key to

transforming traditional farming into a resilient, data-

driven ecosystem.

6 CONCLUSIONS

This research presents a comprehensive and future-

ready framework that redefines the role of IoT in

precision agriculture by addressing the fundamental

limitations of cost, connectivity, usability, and

adaptability. By integrating edge computing, energy-

efficient sensor networks, and blockchain-secured

data logging, the proposed system empowers farmers

with real-time, localized, and actionable insights

while minimizing reliance on continuous internet

access. The inclusion of a farmer-centric interface

and climate-resilient analytics further ensures that the

technology remains accessible, relevant, and practical

across diverse agricultural contexts.

The system's successful deployment across

multiple field scenarios demonstrated measurable

improvements in crop yield, resource utilization, and

operational efficiency. The ability to operate

autonomously, adapt dynamically to environmental

changes, and learn from farmer feedback positions

this solution as a robust alternative to conventional

and cloud-dependent agricultural platforms.

Moreover, the research advances the discourse in

smart farming by embedding traceability, scalability,

and automation into a unified ecosystem. The positive

engagement from farmers, combined with

quantifiable environmental and economic benefits,

ICRDICCT‘25 2025 - INTERNATIONAL CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION,

COMMUNICATION, AND COMPUTING TECHNOLOGIES

highlights the framework’s potential for real-world

adoption and policy integration.

In essence, this study contributes a novel blueprint

for sustainable agricultural transformation one that is

data-driven, intelligent, and deeply rooted in the

needs and realities of the modern farmer. Future work

will focus on expanding the framework’s capabilities

through integration with drones, satellite imagery,

and advanced decision-making models to further

enhance precision and productivity on a global scale.

REFERENCES

Albanese, A., Nardello, M., & Brunelli, D. (2021).

Automated pest detection with DNN on the edge for

precision agriculture. arXiv preprint arXiv:2108.00421

.arXiv

Albanese, A., Nardello, M., & Brunelli, D. (2021).

Automated pest detection with DNN on the edge for

precision agriculture. arXiv preprint arXiv:2108.00421

. arXiv

Dutta, M., Gupta, D., Tharewal, S., Goyal, D., Sandhu, J.

K., Kaur, M., Alzubi, A. A., & Alanazi, J. M. (2025).

Internet of Things-based smart precision farming in

soilless agriculture: Opportunities and challenges for

global food security. arXiv preprint arXiv:2503.13528.

Dutta, M., Gupta, D., Tharewal, S., Goyal, D., Sandhu, J.

K., Kaur, M., Alzubi, A. A., & Alanazi, J. M. (2025).

Internet of Things-based smart precision farming in

soilless agriculture: Opportunities and challenges for

global food security. arXiv preprint arXiv:2503.13528.

Garg, S., Pundir, P., Jindal, H., Saini, H., & Garg, S. (2021).

Towards a multimodal system for precision agriculture

using IoT and machine learning. arXiv preprint

arXiv:2107.04895.

Garg, S., Pundir, P., Jindal, H., Saini, H., & Garg, S. (2021).

Towards a multimodal system for precision agriculture

using IoT and machine learning. arXiv preprint

arXiv:2107.04895.

Giménez Pérez, M. Á., Guerrero-González, A., Cánovas

Rodríguez, F. J., Martínez León, I. M., & Lloret

Abrisqueta, F. A. (2024). Precision agriculture 4.0:

Implementation of IoT, AI, and sensor networks for

tomato crop prediction. Buletin Ilmiah Sarjana Teknik

Elektro, 6(2), 172–181.ResearchGate

Giménez Pérez, M. Á., Guerrero-González, A., Cánovas

Rodríguez, F. J., Martínez León, I. M., & Lloret

Abrisqueta, F. A. (2024). Precision agriculture 4.0:

Implementation of IoT, AI, and sensor networks for

tomato crop prediction. Buletin Ilmiah Sarjana Teknik

Elektro, 6(2), 172–181.ResearchGate

Kumar, L., Ahlawat, P., Rajput, P., & Navsare, R. (2021).

Internet of Things (IoT) for smart precision farming and

agricultural systems productivity: A review. Internatio

nal Journal of Engineering Applied Sciences and

Technology, 5(9), 141–146.ResearchGate

Kumar, L., Ahlawat, P., Rajput, P., & Navsare, R. (2021).

Internet of Things (IoT) for smart precision farming and

agricultural systems productivity: A review.

International Journal of Engineering Applied Sciences

and Technology, 5(9), 141–146.ResearchGate

Kumar, L., Ahlawat, P., Rajput, P., & Navsare, R. (2021).

Internet of Things (IoT) for smart precision farming and

agricultural systems productivity: A review.

International Journal of Engineering Applied Sciences

and Technology, 5(9), 141–146.ResearchGate

Morchid, M., et al. (2025). Smart farming and how IoT and

sensors are changing agriculture. Spectroscopy Online.

Retrieved from https://www.spectroscopyonline.com/v

iew/smart-farming-and-how-iot-and-sensors-are-

changing-agricultureSpectroscopy Online

Morchid, M., et al. (2025). Smart farming and how IoT and

sensors are changing agriculture. Spectroscopy Online.

Retrieved from https://www.spectroscopyonline.com/v

iew/smart-farming-and-how-iot-and-sensors-are-

changing-agricultureSpectroscopy Online

Sattar, K., Arslan, M., Majeed, S., & Iqbal, S. (2025).

Wireless sensor networks data synchronization using

Node MCU memory for precision agriculture

applications. arXiv preprint arXiv:2502.18671.

Sattar, K., Arslan, M., Majeed, S., & Iqbal, S. (2025).

Wireless sensor networks data synchronization using

Node MCU memory for precision agriculture applicati

ons. arXiv preprint arXiv:2502.18671.

Sharma, K., & Shivandu, S. K. (2024). Integrating artificial

intelligence and Internet of Things (IoT) for enhanced

crop monitoring and management in precision

agriculture. Smart Innovation, Systems and

Technologies, 100292. https://doi.org/10.1016/j.sintl.

2024.100292ScienceDirect

Sharma, K., & Shivandu, S. K. (2024). Integrating artificial

intelligence and Internet of Things (IoT) for enhanced

crop monitoring and management in precision agricult

ure. Smart Innovation, Systems andTechnologies, 100

292.https://doi.org/10.1016/j.sintl.2024.100292

ScienceDirect

Sharma, K., & Shivandu, S. K. (2024). Integrating artificial

intelligence and Internet of Things (IoT) for enhanced

crop monitoring and management in precision agricult

ure. Smart Innovation, Systems and Technologies, 100

292. https://doi.org/10.1016/j.sintl.2024.100292

ScienceDirect

A Resilient and Scalable IoTâ

SDriven Precision Agriculture Framework with Edge Intelligence, Climate Adaptability, and

Farmerâ

SCentric Optimization