Exploring the Role of Machine Learning in Advancing Crop Disease

Detection

Ashwini Deshmukh

, Devesh Nawgaje

and Komal Vyas

Institute Shri Sant Gajanan Maharaj College of Engineering Shegaon, India

Department of Electronics and Telecommunication Engineering, India

Keywords: Machine Learning, Support Vector Machine, Convolution Neural Networks, FAO.

Abstract: Crop infections are a significant issue in agriculture, impacting the quality and quantity of produce. Crop

diseases can reduce crop output, resulting in lower yields and financial losses for farmers. Research on

disease control has been conducted in various scientific and technological fields. The study examines

machine learning methods for detecting plant diseases utilising multiple data sources, such as IOT and

image technology. Effective disease control has been demonstrated by the tremendous potential presented

by technological advancements in sensors, data storage, processing power, and artificial intelligence. In

Maharashtra, soybean is cultivated on a large scale and is a highly popular crop. This paper focuses on the

study of various soybean diseases prevalent in the region. Using data from various sensors and machine

learning to develop models for detection, prediction, analysis, and assessment is becoming increasingly

important, according to the research. The growing number and variety of research papers need a literature

assessment to inform future advances and contributions. In this paper machine learning methods are used.

This article discusses how soybean diseases can be detected using various Machine learning algorithms and

can improve plant health status prediction from diverse data sources. The study ends with a discussion of

some contemporary issues and research trends.

1 INTRODUCTION

The issue of crop disease has garnered considerable

attention recently due to its direct influence on the

food supply. Pests and diseases are a key barrier to

achieving optimal productivity. Therefore, it is

crucial to develop effective methods for the

automated identification, diagnosis, and prediction

of pests and diseases affecting agricultural crops.

The utilization of Machine Learning (ML)

techniques is crucial for extracting insights and

correlations from the datasets being examined. The

main aim of this research is to promote the progress

of smart agriculture and precision farming by

advocating for the implementation of methodologies

that empower farmers to minimize the use of

pesticides and agrochemicals while maintaining and

enhancing crop yield quality. As indicated by the

FAO (HAJIMORAD, DOMIER, et al. , 2018), pest

infestations and plant diseases are recognized as key

factors contributing to the reduction of food supply

and sanitation. The occurrence of plant ailments

displays seasonal variations influenced by the

presence of pathogens, environmental conditions,

and crop types. Crops can face stress from various

factors, including abiotic (drought, waterlogging,

salinity), biotic (insects, pests, weeds, viruses), and

climate change (Dixit, Kumar, et al. , 2023).

Pathogens are living organisms that induce diseases,

such as viruses, bacteria, or fungi. The impact on

crops can vary from minor physiological

abnormalities to complete plant death, depending on

the specific disease and growth stage.

Plant diseases can result from biological and

physical factors, including climate change.

Pesticides are used to control damage but can harm

the environment, kill beneficial insects, and lead to

resistance. Identifying sick plant areas can reduce

pesticide use. Traditional methods for diagnosing

plant diseases rely on visual inspections and

chemical assays, which are labor-intensive and

require significant human resources.

360

Deshmukh, A., Nawgaje, D. and Vyas, K.

Exploring the Role of Machine Learning in Advancing Crop Disease Detection.

DOI: 10.5220/0013592400004664

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

In Proceedings of the 3rd International Conference on Futuristic Technology (INCOFT 2025) - Volume 2, pages 360-366

ISBN: 978-989-758-763-4

2 MACHINE LEARNING

MODELS

Machine learning models help researchers

understand data and find out how factors lead to

crop diseases and pests. They process data and

identify important features to perform tasks like

classifying and predicting. In classification, the

model labels new data based on what it learned

before, while in prediction, it estimates values from

input data. By using large amounts of data, such as

images, environmental conditions, and plant health

measurements, these models can detect and diagnose

crop diseases, often before symptoms appear.

Techniques like Convolutional Neural Networks

(CNNs) are great for analysing images, while

Support Vector Machines (SVM) and Random

Forests handle structured data well. These models

learn from examples, making them accurate in

predicting diseases. Using machine learning in

farming helps detect diseases more accurately and

quickly, reducing crop loss and improving yields.

The following machine learning models show how

these algorithms work for detecting crop diseases

and their accuracy.

2.1 Support vector machine (SVM)

SVM is a machine learning model that creates a

boundary (called a hyperplane) to separate two

classes of data. SVM can efficiently classify disease

symptoms based on features extracted from images

or sensor data, enabling accurate and timely

identification of issues affecting crops.

2.2 Random Forest(RF)

Random Forest is a popular machine learning

method that uses many decision trees to make

accurate predictions. Random Forest is particularly

good at handling complex data and can accurately

determine if a crop is healthy or diseased.

2.3 K-Nearest Neighbours (KNN)

The k-Nearest Neighbours(k-NN) algorithm is a

straightforward and intuitive method used for both

classification and regression tasks. One of the key

features of k-NN is its simplicity, as it does not

require a complex model-building phase.

2.4 Convolution Neural Networks

(CNNs)

Convolution Neural Networks (CNNs) are a type of

deep learning algorithm particularly effective for

analysing visual data, such as images of crops. In

crop disease detection, CNNs can sort images of

plant leaves into categories such as "healthy" or

"diseased" based on these features.diagnosis.

immediate adjustments and reduce the need for

remakes. Additionally, AI-powered software can

predict the longevity of restorations by analysing

wear patterns and material properties, helping to

optimize treatment plans.

3 CROP DISEASES

In India, crop diseases are increasing significantly,

especially in Maharashtra, where the situation is

more severe. This rise in diseases is leading to more

crop infections and reduced yields. In Maharashtra,

soybean is one of the most common crops affected

by these issues. Table 1 outlines the favourable

conditions that contribute to the spread of diseases in

soybeans. In this section, we discuss the diseases

that affect soybean crops. The evolution of

publications in crop disease detection models is

shown in fig 1. later, it covers how machine learning

algorithms can detect these soybean diseases and the

accuracy they provide in doing so.

Figure 1: Crop Research Distribution by Focus Area

Exploring the Role of Machine Learning in Advancing Crop Disease Detection

361

Table 1: Favourable conditions for disease spread in

soybean.

Disease Temperature

(

°C

)

Moisture Wetness

Duration

Soybean

Mosaic

Virus

(SMV) 20

–

30 High

Indirect

(Aphid

activity)

Soybean

Cyst

Nematode

(

SCN

)

–

30 Moderate

Indirect

(Soil

conditions

)

Frogeye

Leaf S

ot 22

–

30 Hi

h 6

–

Brown

Spot 22

–

28 High ≥8

Soybean

Rust 15

–

High

(>90%) 6

–

Leaf Spot

Diseases 25

–

30 Hi

h 6

–

4 LITERATURE REVIEW

4.1 SMV detection in soybean

Soybean Mosaic Virus (SMV) is a major threat to

soybean crops, causing yield losses and poor seed

quality. It spreads through aphids and infected seeds,

leading to symptoms like leaf mottling, stunted

growth, and reduced pods. Researchers are working

on breeding resistant soybean varieties, improving

pest control, and developing diagnostic tools for

early detection.

In paper (Guia, Feia, et al. , 2021), the author

introduced an Novel approach combining

hyperspectral imaging with a CNN-SVM model to

detect and grade Soybean Mosaic Virus (SMV)

severity into three levels. The CNN-SVM model

achieved 96.67% training accuracy and 94.17% test

accuracy, outperforming standalone CNN models,

especially with smaller sample sizes. This method

proved effective in handling limited data and

addressing hyperspectral redundancy, with potential

for early-stage disease detection. Future research

could explore the model's scalability for field

conditions and its application to other crop diseases.

The methodology employed in the study

involved utilizing a pre-trained Mask R-CNN

model, specifically initialized with the ResNet50

backbone, to detect and segment soybean leaf

diseases. The dataset comprised 3,127 RGB images

collected from various regions in India, including

both diseased and disease-free leaves. The model

was fine-tuned on this dataset, and its performance

was evaluated using a separate test dataset. The

detection accuracy was assessed at different

confidence levels, revealing a maximum accuracy of

over 85% at a minimum confidence level of 0.90.

This study (Cui, Chen, et al. , 2011)] employs

optimized Convolutional Neural Networks (CNNs)

with transfer learning using pretrained models like

AlexNet and GoogleNet to detect soybean mosaic

virus (SMV). The models, trained on 649 diseased

and 550 healthy soybean leaf images, achieved

accuracy rates of 98.75% and 96.25%, respectively,

demonstrating their potential for early and precise

disease detection. Future directions include creating

mobile applications for real-time diagnosis on low-

power devices and extending the approach to cover

other diseases and pests, promoting sustainable

agriculture and enhanced crop yields.

4.2 Charcoal rot detection in soybean

Charcoal rot, caused by the fungus Macrophomina

phaseolina, is a significant disease affecting

soybeans, especially in hot and dry areas like

Maharashtra, India. It results in early leaf loss, stem

rot, and root decay, hindering the plant's ability to

absorb water and nutrients. The fungus’s ability to

persist in soil makes it challenging to manage.

Research is focused on developing resistant soybean

varieties, understanding the fungus's genetic traits,

and improving soil management practices.

Advanced methods and field trials are crucial for

detecting and controlling the disease more

effectively.

This study uses machine learning (ML) to detect

and classify charcoal rot in soybean plants caused by

Macrophomina phaseolina. With a dataset of 2,000

plants, ML models achieved 95.76% accuracy,

highlighting ML's potential for early disease

detection and better crop management. However, the

small dataset limits generalizability. Future research

could expand the dataset and explore other features

or algorithms, with ML offering farmers valuable

insights for combating diseases like charcoal rot.

This paper (Khalili, Kouchaki, et al. , 2020)

predicts charcoal rot in soybean crops using machine

learning (ML). The study used a dataset of 2,000

healthy and infected plants, with physiological and

morphological features as inputs. Gradient Tree

Boosting (GBT) outperformed other classifiers,

achieving 96.25% sensitivity and 97.33%

specificity. The research suggests combining disease

models with domain knowledge for automated early

detection systems, improving disease management,

reducing pesticide use, and enhancing crop

INCOFT 2025 - International Conference on Futuristic Technology

362

sustainability, thereby minimizing economic losses

and improving agricultural practices.

The study (Nagasubramanian, Jones, et al. ,

2018) used Genetic Algorithm (GA) and Support

Vector Machine (SVM) to identify charcoal rot

disease in soybeans early, with hyperspectral

imaging selecting six optimal bands from 240

wavelengths. It achieved 97% accuracy and an F1-

score of 0.97, with early detection possible by day

three post-inoculation. Future plans include testing

in field conditions and expanding to diverse soybean

genotype.

4.3 Soybean Brown Spot detection in

soybean

Soybean Brown Spot, caused by Septoria glycina,

affects crops worldwide, particularly in Maharashtra,

India. It causes brown spots on leaves, leading to

early leaf drop and reduced photosynthesis. The

disease thrives in warm, humid conditions and can

reduce yields if it strikes early. Researchers are

working on resistant soybean varieties, better

fungicide use, and farming practices to manage the

disease. Technologies like remote sensing and AI

are also being used for early detection and timely

intervention.

This research (Miao, Zhou, et al. , 2023) focuses

on detecting soybean diseases, particularly brown

spot, using a deep learning framework. It involved

preprocessing images with the Grabcut algorithm

and segmenting lesions using HSI and Lab color

spaces for better accuracy. A CNN with continuous

layers and sparse Maxout units was developed to

improve feature extraction and reduce overfitting,

achieving 94.87% accuracy. However, the complex

CNN structure increases computational demands.

Future work could focus on dimensionality

reduction to improve efficiency without losing

accuracy, highlighting the potential of AI in crop

disease management.

This study (Bhujbal, Mandale, et al. , 2023)

presents a method for detecting soybean brown spot

using image processing and deep learning. High-

definition images are processed to remove

backgrounds using the Grabcut algorithm, and

lesions are segmented using HSI and Lab color

spaces. A convolutional neural network (CNN) with

a sparse Max-out activation function enhances

feature extraction and minimizes overfitting. The

model outperformed traditional methods, achieving

high accuracy. Future work includes extending this

approach to other crop diseases, improving

efficiency, and developing real-time applications for

better agricultural management.

The paper (Kashyap, Shrivastava, et al. , 2022)

introduces a deep learning-based system for

detecting soybean foliar diseases using a

Convolutional Neural Network (CNN). It employs a

dataset of soybean leaf images that are preprocessed

and augmented to enhance model performance. The

system shows high accuracy in detecting disease,

outperforming traditional methods. Future directions

include adapting the model for other crops,

integrating it with IoT for real-time disease

monitoring, and applying it in precision agriculture

for targeted treatment, ultimately improving crop

health and management.

4.4 Soybean rust detection in soybean

Soybean rust, caused by Phakopsora pachyrhizi and

Phakopsora meibomiae, is a significant threat to

soybean crops worldwide, reducing both yield and

quality. It manifests as reddish-brown spots on the

underside of leaves, causing leaf drop and limiting

photosynthesis. The disease thrives in warm, humid

conditions and spreads rapidly through airborne

spores, making it difficult to control. Farmers

manage it through resistant varieties, fungicides, and

crop rotation. Research focuses on understanding the

disease, developing resistant varieties, and

improving early detection for better control.

This study (Santana, Otone, et al. 2024) used a

6x3 factorial design to evaluate ML algorithms for

classifying Asian soybean rust severity in the

2022/2023 harvest. Hyperspectral analysis (350–

2500 nm) identified spectral signatures for healthy

and 25% to 50% severity levels. Algorithms like

ANN, REPTree, J48, Random Forest, SVM, and

Logistic Regression were tested, with SVM showing

the best accuracy. Future work could explore more

ML techniques, environmental factors, and real-time

data for better disease management.

This study (Ferraz, Santiago, et al. , 2024)

employs UAV-mounted multispectral sensors and

the Random Forest algorithm to assess defoliation

caused by Asian soybean rust in soybean plants. Key

inputs, including vegetation indices (e.g., WDRVI,

MPRI) and spectral bands (red-edge, NIR), achieved

94% accuracy, highlighting the potential of this

approach for precise crop health monitoring. Future

work could adapt this method to other diseases and

agricultural settings

The Research work (Dixit, Kumar, et al. , 2023)

presents a deep learning approach for detecting

soybean leaf diseases in two major Indian regions.

Exploring the Role of Machine Learning in Advancing Crop Disease Detection

363

The methodology involves collecting a dataset of

soybean leaf images, followed by preprocessing and

augmentation, with a Convolutional Neural Network

(CNN) used for disease classification. The model

achieves high accuracy in identifying diseases like

bacterial blight and downy mildew, with strong

performance metrics including precision and recall.

Future directions include integrating the system with

mobile apps and drones for real-time disease

monitoring, as well as expanding the model's use to

other crops for broader agricultural application.

4.5 Frogeye leaf spot detection in

soybean

Frogeye leaf spot, a disease triggered by the fungus

Cercospora sojina, is a major problem for soybean

crops. It causes round, grayish spots with dark edges

on the leaves, which can make the leaves drop off

early and lower the plant’s ability to make food.

This disease spreads in warm, humid conditions and

is carried by wind and rain. To manage frogeye leaf

spot, farmers use soybean varieties that resist the

disease, apply fungicides, and rotate crops to keep

the fungus in check. Research is looking into the

different types of the fungus, developing more

resistant soybean varieties, and creating better ways

to predict when the disease might strike. These

efforts are important for managing frogeye leaf spot

and protecting soybean crops.

The paper (Shelke, Degadwala, et al. , 2024)

introduces a Conv-LSTM model for multi-class

classification of soybean leaf diseases, combining

CNNs for spatial features and LSTMs for sequential

patterns. Using preprocessed image data, the model

achieves high accuracy in identifying various

diseases. Future scope includes real-time

deployment with drones and IoT devices and

extending the approach to other crops and

environments for broader agricultural use.

This study explores a machine learning approach

for detecting soybean leaf diseases using algorithms

like Support Vector Machines and Random Forest.

After preprocessing the image dataset and extracting

key features, the model achieves high accuracy in

disease identification. Future plans include

integrating the system into mobile platforms for

farmer accessibility and expanding its application to

other crops.

The study (Bouaafia, Ahmed, et al. , 2024)

introduces a cost-effective deep learning approach

using CNNs to detect and localize leaf diseases from

image datasets with high accuracy. It aims to

enhance agricultural practices, with future plans to

expand disease coverage, improve real-time

detection, and deploy in field conditions.

4.6 The Soybean Cyst Nematode

detection in soybean

The Soybean Cyst Nematode (SCN) is a major

threat to soybean crops, attacking roots and causing

poor growth, yellowing, and reduced yield. SCN

forms cysts on roots, containing eggs that can

survive in soil for years, making it hard to control.

Infestations can cause crop losses of 10% to 30%.

Management includes crop rotation, using resistant

soybean varieties, and integrated pest management

(IPM). As SCN can adapt, research is focused on

genetic resistance, biological control, and molecular

techniques to develop more effective control

methods.

The paper (Jjagwe, Chandel, et al. , 2024)

evaluates the impact of nematode infestations on

soybean yields using aerial multispectral imagery

and machine learning. Drone capture multispectral

data to identify crop stress, and machine learning

models analyze this data to classify infestation levels

and estimate yield losses. The approach achieves

high accuracy in detecting nematode effects,

offering a scalable solution for large-scale

monitoring. Future scope includes improving model

precision, expanding to other crop pests, and

integrating the system into real-time pest

management frameworks.

The paper (Santos, Bastos, et al. , 2022)

examines the use of remote sensing and machine

learning to detect nematode damage in soybean

crops. By analyzing multispectral imagery with

machine learning models, the study accurately

identifies stress caused by nematodes. Future

directions include refining the model, expanding its

application to other crop stressors, and integrating it

into real-time monitoring systems for better crop

management.

The paper (Akintayo, Lee, et al. , 2016)

introduces an end-to-end convolutional selective

auto encoder for detecting soybean cyst nematode

eggs. This deep learning model effectively

highlights key features of eggs while reducing noise,

resulting in high detection accuracy. Future work

focuses on improving scalability, applying the

method to other nematode species, and integrating it

into real-time agricultural pest monitoring systems.

INCOFT 2025 - International Conference on Futuristic Technology

364

5 DISCUSSION

As discussed Soybean is one of the most widely

cultivated crops globally, serving as a vital source of

protein and oil. However, the productivity and

quality of soybeans are significantly affected by

various diseases, such as rust, mosaic virus, charcoal

rot, brown spot. Accurate and early detection of

these diseases is critical to minimizing crop losses

and ensuring crop yield. Based on the review of

soybean crop diseases it is observed that CNN

models consistently perform better than Mask R-

CNN for SMV detection (Guia, Feia, et al. , 2021),

(Cui, Chen, et al. , 2011). The highest accuracy

96.25% is achieved by CNN with a dataset of 1199

images for SMV detection. A CNN-based model

achieves 95.76% accuracy for charcoal rot disease

(Khalili, Kouchaki, et al. , 2020),

(Nagasubramanian, Jones, et al. , 2018) while

sensitivity and specificity metrics for another dataset

(2000 samples) are reported as 96.25% and 97.33%,

indicating high reliability. CNN models are

primarily used, achieving up to 94.87% accuracy for

brown spot detection (Miao, Zhou, et al. , 2023),

(Bhujbal, Mandale, et al. , 2023), (Kashyap,

Shrivastava, et al. , 2022) .Random Forest (RF)

achieves95% accuracy, while SVM utilizes

hyperspectral images for Rust detection (Santana,

Otone, et al. 2024), (Ferraz, Santiago, et al. , 2024).

6 CONCLUSION

In Machine learning is becoming essential for

detecting crop diseases, significantly improving

agricultural productivity. By analysing large

datasets, these models can accurately diagnose

diseases like rust and leaf spot, with accuracy rates

up to 98%. However, the effectiveness of these

models can vary due to factors like data quality and

regional differences in disease symptoms. As

machine learning technologies advance, they could

be utilized to develop models that analyse soybean

images and other relevant data to detect SMV

symptoms more accurately and efficiently. While

promising, continued research is needed to enhance

the accuracy for different methodologies of machine

learning models across different crops and

conditions, ultimately supporting more sustainable

farming practices.

7 FUTURE SCOPE

The future scope includes exploring advanced

models like Vision Transformers and hybrid

approaches to improve accuracy across various

soybean diseases. Enhancing datasets with diverse

inputs, such as multispectral and hyperspectral

images, can improve the ability of models to

generalize and accurately identify diseases. These

advanced imaging methods offer detailed spectral

data, allowing models to better differentiate between

healthy and affected plants.

REFERENCES

M. R. HAJIMORAD1, L. L. DOMIER2, S.A. TOLIN3,

S.A.WHITHAM4 AND M. A. SAGHAIMAROOF5,

“Soybean mosaic virus: a successful poty virus with a

wide distribution but restricted natural host range”,

MOLECULAR PLANT PATHOLOGY (2018) 19(7),

1563–1579.

S Dixit, A Kumar, A Haripriya, K Bohre, K Srinivasan,

“Classification and recognition of soybean leaf

diseases in Madhya Pradesh and Chhattisgarh using

Deep learning methods” ,

10.1109/PCEMS58491.2023.10136030.

Elham Khalili, Samaneh Kouchaki, Shahin Ramazi and

Faezeh Ghanati, “Machine Learning Techniques for

Soybean Charcoal Rot Disease Prediction”,Frontiers

in plant science ,14 Dec 2020.

S Shelke, S Degadwala, “Multi-Class Recognition of

Soybean Leaf Diseases using a Conv-LSTM” ,

https://doi.org/10.32628/CSEIT2410217

Sahil Bhujbal, Pradnya Mandale, Vaishnavi Aher,

Rushikesh Wable , “Soybean Leaf Disease Detection”

, International Journal for Research in Applied Science

& Engineering Technology (IJRASET) .

D.C. Santana, J.D.d.Q. Otone, F.H.R. Baio, L.P.R.

Teodoro, M.E.M. Alves, C.A. da Silva Junior, P.E.

Teodoro, “Machine learning in the classification of

asian rust severity in soybean using hyperspectral

sensor, Spectrochim. Acta A Mol. Biomol. Spectrosc.

313 (2024) 124113.

Preeti Jha, Aruna Tiwari, Neha Bharill, “Machine learning

algorithm for soybean leaf disease detection”,Journal

of Oilseeds Research, 40 (Specialissue).

Jiangsheng Guia, Jingyi Feia, Zixian Wua, Xiaping Fub,

Alou Diakitea ,“Grading method of soybean mosaic

disease based on hyperspectral imaging technolog” ,

Information Processing inAgriculture 8 (2021) 380–

385.

M. Kumar , N. S. Chandel , D. Singh and L. S. Rajput,

“Soybean Disease Detection and Segmentation Based

on Mask-RCNN Algorithm” , Journal of Experimental

Agriculture International.

Adedotun Akintayo, Nigel Lee, Vikas Chawla, “An end-

to-end convolutional selective autoencoder approach

Exploring the Role of Machine Learning in Advancing Crop Disease Detection

365

to Soybean Cyst Nematode eggs detection”

arXiv:1603.07834v1 [cs.CV] 25 Mar 2016

Xiaoyan Cui, Xin Chen and Aiming Wang, “Detection,

Understanding and Control of Soybean Mosaic Virus”,

Soybean - Molecular Aspects of Breeding.

Letícia Bernabé Santos , Leonardo Mendes Bastos, Pedro

Luiz Martins Soares 5, Ignacio Antonio Ciampitti ,

Mailson Freire de Oliveira , andRouversonPereira da

Silva, “Identifying Nematode Damage on Soybean

through Remote Sensing and Machine Learning

Techniques”, Agronomy 2022, 12, 2404.

https://doi.org/10.3390/agronomy12102404

P Jjagwe, AK Chandel, DB Langston, “Impact

Assessment of Nematode Infestation on Soybean Crop

Production Using Aerial Multispectral Imagery and

Machine Learning”, Appl. Sci. 2024, 14(13), 5482;

https://doi.org/10.3390/app14135482.

Y Kashyap, SS Shrivastava, R Sharma, “An Improved

Soybean Foliar Disease Detection System using Deep

Learning” 2022 IEEE Conference on Interdisciplinary

Approaches in Technology

Marcelo Araújo Junqueira Ferraz, Afrânio Gabriel da

Silva Godinho Santiago, Adriano Teodoro Bruzi,

Nelson Júnior Dias Vilela, Gabriel Araújo e Silva

Ferraz, “Defoliation Categorization in Soybean with

Machine Learning Algorithms and UAV Multispectral

Data” ,

Koushik Nagasubramanian , Sarah Jones, Soumik Sarkar ,

Asheesh K. Singh , Arti Singh , Baskar

Ganapathysubramanian , “Hyperspectral band

selection using genetic algorithm and support vector

machines for early identification of charcoal rot

disease in soybean” , Plant methods, 2018•Springer .

Adeboye, O.B.; Schultz, B.; Adekalu, K.O.; Prasad, K.

Modelling of Response of the Growth and Yield of

Soybean to Full and Deficit Irrigation by Using

Aquacrop. Irrig. Drain. 2017, 66, 192–205.

https://doi.org/10.1002/ird.2073.

B Tej, S Bouaafia, OB Ahmed, MA Hajjaji, A Mtibaa,

“Affordable Deep learning-based Leaf Disease

Detection and Localization for Precision Agriculture” ,

2024 IEEE 7th …, 2024 - ieeexplore.ieee.org

Yousfi, S.; Marín, J.; Parra, L.; Lloret, J.; Mauri, P.V.

Remote Sensing Devices as Key Methods in the

Advanced Turfgrass Phe notyping under Different

Water Regimes. Agric. Water Manag. 2022, 266,

107581. https://doi.org/10.1016/j.agwat.2022.107581.

Tiago Domingues , Tomás Brandão , andJoãoC.Ferreira ,

“Machine Learning for Detection and Prediction of

Crop Diseases and Pests: A Comprehensive Survey” ,

Agriculture 2022, 12, 1350..

MaryamOuhami , Adel Hafiane , Youssef Es-Saady ,

MohamedElHajji and Raphael Canals, “Computer

Vision, IoT and Data Fusion for Crop Disease

Detection Using Machine Learning: A Survey and

Ongoing Research” , Remote Sens. 2021, 13, 2486.

E. Miao, Guixia Zhou ,andShengxue Zhao, “Research on

Soybean Disease Identification Method Based on

Deep Learning” , Hindawi Mobile Information

Systems.

Dr. Nanda Ashwin, Uday Kumar Adusumilli, Prof.

Kemparaju N, Lakshmi Kurra , “A Machine Learning

Approach to Prediction of Soybean Disease” , doi :

https://doi.org/10.32628/IJSRSET219416Research,

99, 1–5.

INCOFT 2025 - International Conference on Futuristic Technology

366