A Review on Deep Learning Approaches for Plant Leaf Disease Detection and Pesticide Recommendation

Abstract

Crop sustainability is an urgent issue in the world, and plant diseases are a significant reason for crop yield and food security restrictions. Conventional manual disease detection procedures are time-consuming and frequently inaccurate. Deep learning, particularly Convolutional Neural Networks (CNNs), has made automated and accurate plant disease diagnosis from leaf images possible in recent years. This review overviews current deep learning methods for the detection of plant leaf diseases and delves into models with pesticide recommendation systems. The review classifies studies into CNN-based models, classical machine learning methods, hybrid models, and image processing approaches. It also identifies systems with region-specific pesticide recommendations. Issues like data shortage, generalization of models, and compliance with regulations are addressed, in addition to directions for the future like mobile deployment, transfer learning, and IoT integration. This thorough review is designed to direct future research toward smart, scalable agriculture solutions.

Introduction

Agriculture is vital globally, especially in agrarian countries like India, where many depend on farming. Early, accurate plant disease detection is crucial to protect crop yield but is traditionally manual, slow, and often inaccessible to small farmers. Recent advances in artificial intelligence (AI), particularly deep learning and Convolutional Neural Networks (CNNs), have revolutionized automated plant disease detection from leaf images by extracting complex features without manual effort.

This review surveys deep learning approaches for detecting plant leaf diseases and emerging systems that integrate automated pesticide recommendations tailored to regional agricultural data. It covers fundamentals of CNN architectures, the role of recommendation systems, and various machine learning (ML) and hybrid models used for classification and diagnosis.

Key findings from literature include:

• CNN models like AlexNet, VGG19, DenseNet, and custom architectures achieve high accuracy (over 98%) in classifying plant diseases across diverse crops.

• Hybrid approaches combine image processing, ML, rule engines, and knowledge graphs to improve early and precise detection.

• Image processing techniques enhance ML effectiveness through better feature extraction and preprocessing.

• Pesticide recommendation systems are evolving, linking disease detection to treatment advice using databases, GIS data, and local language support.

• Herbal treatments such as Aloe Vera show promise as natural antifungal and antimicrobial agents.

• Extensive datasets like PlantVillage support benchmarking and improving AI models.

• Additional applications include building comprehensive diagnostic knowledge bases and exploring plant-based disease control methods.

The review highlights ongoing challenges and proposes future directions to further develop AI-powered, user-friendly tools that empower farmers and agronomists for smarter, timely disease management and sustainable agriculture.

Conclusion

Deep learning has become a revolutionary technology for the detection of plant disease with high accuracy and automation. Utilizing CNNs and combining them with pesticide recommendation systems has brought us substantially closer to the solutions of smart farming. Nonetheless, there are issues like data quality, generalization, and applicability in real-world scenarios. Solving these problems with lightweight models, explainable AI, and local tools will be central to unlocking the full potential of these systems in sustainable agriculture.

References

[1] Muhammad et al., \"Plant Leaf Disease Detection Using Deep Learning and Traditional Classifiers,\" IJIRCCE, 2021. [2] Shankar et al., \"A Deep Convolutional Neural Network for Plant Disease Detection,\" IJARECE, 2022. [3] Nishita et al., \"Transfer Learning for Multi-Crop Disease Classification,\" IJARCCE, 2022. [4] Vaidya et al., \"CNN-Based Citrus Crop Health Monitoring System,\" IJERT, 2022. [5] Tej et al., \"DenseNet121 for Leaf Disease Detection in Tomato and Pepper,\" JETIR, 2023. [6] Patil et al., \"Banana Leaf Disease Detection Using CNN,\" IJERT, 2021. [7] Balakrishnan et al., \"IoT-Enhanced Plant Disease Identification System,\" IJARCET, 2022. [8] Bhagat et al., \"Support Vector Machines with Grid Search for Plant Health,\" IJIERT, 2020. [9] Shruthi et al., \"Comparison of ML Models for Leaf Disease Detection,\" IJERT, 2021. [10] Harsha et al., \"Pesticide Recommendation using AI and ISO Standards,\" IJRASET, 2022. [11] Deshpande et al., \"AI-Driven Disease and Pest Knowledge Platform,\" JETIR, 2022. [12] Gauri et al., \"User Interface for Disease Diagnosis and Pesticide Selection,\" IJRESM, 2022. [13] Amritraj et al., \"YOLOv5 + CNN for Real-Time Leaf Disease Detection,\" IJRTET, 2023. [14] Kalaivani et al., \"Preprocessing Techniques for Early Disease Detection,\" IJSRET, 2021. [15] Dash et al., \"Red-Green Channel for Maize Leaf Analysis,\" IJAER, 2021. [16] Selvi et al., \"Tomato Disease Detection using HOG + SVM,\" IJERT, 2021. [17] Bairwa et al., \"Signature-Based Machine Learning Model for Tomatoes,\" IJESM, 2022. [18] Malayil et al., \"Clustering-Based Detection of Cardamom Diseases,\" JETIR, 2022. [19] Jamadar et al., \"A Pesticide-Integrated CNN Approach for Cotton Diseases,\" IJERT, 2021. [20] Khandelwal et al., \"ML and Image Thresholding for Plant Health Monitoring,\" IJSR, 2021. [21] Froldi et al., \"Phytochemical Studies on Aloe Vera for Disease Resistance,\" Bioagro, 2020. [22] Babu et al., \"Aloe Vera Proteomics for Disease Response,\" IJBB, 2021. [23] Ahmmed et al., \"Fungal and Genetic Testing on Aloe Samples,\" JPP, 2021. [24] Sánchez et al., \"Therapeutic Potential of Aloe Vera for Crop Health,\" IJNPR, 2020. [25] Tandekar et al., \"Benchmarking ML and CNN Models on PlantVillage,\" IJERT, 2022. [26] Renuka et al., \"Performance Evaluation of CNN Models on Standard Data,\" JETIR, 2021. [27] Kethineni et al., \"Custom CNN Trained on Indian Crop Dataset,\" IJRASET, 2022. [28] Sahu et al., \"Random Forest Boosted CNN for Leaf Disease Classification,\" IJERT, 2022. [29] N.Sahu et al., \"Data Augmentation for Improved CNN Accuracy in Agriculture,\" IJRESM, 2022. [30] Sumair Aziz et al., \"LTrIDP Feature Extraction in Plant Leaf Classification,\" IJIRCCE, 2023. [31] Z. Omar et al., \"Disease Signature Mapping Using Machine Learning,\" JAI, 2022. [32] N. Kannan et al., \"Leaf Segmentation + Random Forest Approach,\" IJTET, 2022. [33] S. Amritraj et al., \"Real-Time Leaf Disease Detection Using CNN,\" IJERT, 2023. [34] N. Chaudhary et al., \"CNN for Citrus Leaf Disease Detection,\" JAI, 2021. [35] S. Sumana et al., \"CNN-Based Detection of Pomegranate Diseases,\" IJAEM, 2022. [36] M. Bhattacharya et al., \"Deep CNN for Multi-Class Plant Disease Detection,\" JISRS, 2021. [37] Uda et al., \"Antibacterial Evaluation of Herbal Extracts on Crops,\" IJAMS, 2020. [38] Ahmadi et al., \"Aloe Vera and Fungus Resistance Studies,\" JPP, 2021. [39] T. Sarika et al., \"Web-Enabled CNN Model for Smart Farming,\" IJERT, 2022. [40] K. Bhosale et al., \"Image Processing-Based Disease Classifier for Chilli Plants,\" IJRASET, 2021. [41] D. Sharma et al., \"Smartphone Leaf Disease Detection using AI,\" IJERT, 2021. [42] M. Thomas et al., \"Deep Transfer Learning in Leaf Analysis,\" IJCSC, 2022. [43] P. Ramesh et al., \"Smart Agricultural Monitoring System,\" IJRESM, 2021. [44] M. Pal et al., \"Cloud-Based Plant Disease Diagnosis with CNN,\" JETIR, 2022. [45] H. Ali et al., \"Fuzzy Logic-Based Disease Severity Estimator,\" IJRASET, 2022. [46] P. Verma et al., \"Deep Neural Networks in Crop Disease Classification,\" IJERT, 2022. [47] R. Waghmare et al., \"VGG16 Implementation for Cotton Leaf Disease Detection,\" JAI, 2022. [48] R. Joshi et al., \"Custom Dataset for Real-World Plant Disease Training,\" IJRASET, 2022. [49] Pawar et al., \"Remote Disease Sensing via Drone-Enabled Imaging,\" JISR, 2023. [50] D. Mahajan et al., \"Analysis of Agricultural Field Images with ML,\" IJERT, 2022. [51] V. Kale et al., \"Precision Agriculture and Real-Time Leaf Scanning,\" IJRASET, 2023. [52] R. Raut et al., \"Hybrid CNN-MLP Architecture for Disease Classification,\" IJERT, 2022. [53] J. Patil et al., \"Edge AI for Plant Disease Diagnosis,\" IJCSC, 2023. [54] Salunkhe et al., \"Image Segmentation Using U-Net in Leaf Analysis,\" JETIR, 2022. [55] P. Jadhav et al., \"Knowledge-Based Diagnostic System for Crops,\" IJRTE, 2021. [56] Patil et al., \"Disease Prediction Using Decision Trees,\" IJERT, 2022. [57] T. More et al., \"YOLO-Based Real-Time Plant Protection Assistant,\" IJRASET, 2022. [58] S. Sontakke et al., \"Pest Alert System Using CNN,\" IJSER, 2022. [59] Jain et al., \"Multi-Crop Leaf Classification System,\" IJERA, 2021. [60] Rathod et al., \"KNN and SVM Comparative Study for Disease Identification,\" IJERT,2022. [61] V. Gole et al., \"Real-Time Disease Tracking Using Mobile Sensors,\" JAI, 2022. [62] N. Mane et al., \"AI-Supported Diagnosis of Tomato Leaf Curl Virus,\" IJCSC, 2021. [63] H. Mule et al., \"Integrated Pest Management with DL Models,\" IJRASET, 2021. [64] P. Naik et al., \"Crop Advisory Chatbot Using NLP and CNN,\" IJERT, 2023. [65] Zope et al., \"Automated Treatment Plan for Leaf Diseases,\" IJCSC, 2023. [66] R. Kale et al., \"High-Performance CNN for Image-Based Crop Analysis,\" IJRASET, 2023. [67] P. Bhusari et al., \"Smart Leaf Scanner App for Rural Farmers,\" IJAEM, 2022. [68] Shah et al., \"Mobile Interface for CNN-Based Disease Alerting,\" JETIR, 2022. [69] N. Talekar et al., \"Federated CNN for Crop Disease Privacy,\" IJERT, 2023. [70] S. Kharat et al., \"AI-Based Fertilizer & Disease Advisor,\" IJRASET, 2022. [71] P. Dhawale et al., \"Visual ML Pipeline for Agricultural Risk Management,\" IJERT, 2021. [72] M. Pawar et al., \"Combined Color & Texture Analysis for Leaf Diagnosis,\" IJCSC, 2022. [73] R. Bidkar et al., \"Custom Rule-Based System for Local Crop Issues,\" IJRASET, 2021. [74] H. Kumbhar et al., \"Benchmarking Lightweight CNNs for Agriculture,\" IJERT, 2022. [75] V. Jagtap et al., \"Integration of Crop Alerts with Weather Data,\" IJRESM, 202

Copyright

Copyright © 2025 Dr. (Mrs.)J. R. Pansare, Urja Awasarmol, Ayush Shastrakar, Sanket Niture. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.