Empowering Smallholder Farmers with UAV-Based Early Cotton Disease Detection Using AI

Early detection of cotton diseases is critical for safeguarding crop yield and minimizing agrochemical usage. However, most state-of-the-art systems rely on multispectral or hyperspectral sensors, which are costly and inaccessible to smallholder farmers. This paper introduces CottoNet, a lightweight...

Full description

Saved in:
Bibliographic Details
Main Authors: Halimjon Khujamatov, Shakhnoza Muksimova, Mirjamol Abdullaev, Jinsoo Cho, Cheolwon Lee, Heung-Seok Jeon
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Drones
Subjects:
Online Access:https://www.mdpi.com/2504-446X/9/5/385
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849327645172432896
author Halimjon Khujamatov
Shakhnoza Muksimova
Mirjamol Abdullaev
Jinsoo Cho
Cheolwon Lee
Heung-Seok Jeon
author_facet Halimjon Khujamatov
Shakhnoza Muksimova
Mirjamol Abdullaev
Jinsoo Cho
Cheolwon Lee
Heung-Seok Jeon
author_sort Halimjon Khujamatov
collection DOAJ
description Early detection of cotton diseases is critical for safeguarding crop yield and minimizing agrochemical usage. However, most state-of-the-art systems rely on multispectral or hyperspectral sensors, which are costly and inaccessible to smallholder farmers. This paper introduces CottoNet, a lightweight and efficient deep learning framework for detecting early-stage cotton diseases using only RGB images captured by unmanned aerial vehicles (UAVs). The proposed model integrates an EfficientNetV2-S backbone with a Dual-Attention Feature Pyramid Network (DA-FPN) and a novel Early Symptom Emphasis Module (ESEM) to enhance sensitivity to subtle visual cues such as chlorosis, minor lesions, and texture irregularities. A custom-labeled dataset was collected from cotton fields in Uzbekistan to evaluate the model under realistic agricultural conditions. CottoNet achieved a mean average precision (mAP@50) of 89.7%, an F1 score of 88.2%, and an early detection accuracy (EDA) of 91.5%, outperforming existing lightweight models while maintaining real-time inference speed on embedded devices. The results demonstrate that CottoNet offers a scalable, accurate, and field-ready solution for precision agriculture in resource-limited settings.
format Article
id doaj-art-56044ea9c5b945dab4549abc7a5144e2
institution Kabale University
issn 2504-446X
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Drones
spelling doaj-art-56044ea9c5b945dab4549abc7a5144e22025-08-20T03:47:49ZengMDPI AGDrones2504-446X2025-05-019538510.3390/drones9050385Empowering Smallholder Farmers with UAV-Based Early Cotton Disease Detection Using AIHalimjon Khujamatov0Shakhnoza Muksimova1Mirjamol Abdullaev2Jinsoo Cho3Cheolwon Lee4Heung-Seok Jeon5Department of Computer Engineering, Gachon University, Seognam-daero, Sujeong-gu, Seongnam-si 1342, Republic of KoreaDepartment of Computer Engineering, Gachon University, Seognam-daero, Sujeong-gu, Seongnam-si 1342, Republic of KoreaDepartment of Information Systems and Technologies, Tashkent State University of Economics, Tashkent 100066, UzbekistanDepartment of Computer Engineering, Gachon University, Seognam-daero, Sujeong-gu, Seongnam-si 1342, Republic of KoreaDepartment of Computer Engineering, Konkuk University, Chungju 05029, Republic of KoreaDepartment of Computer Engineering, Konkuk University, Chungju 05029, Republic of KoreaEarly detection of cotton diseases is critical for safeguarding crop yield and minimizing agrochemical usage. However, most state-of-the-art systems rely on multispectral or hyperspectral sensors, which are costly and inaccessible to smallholder farmers. This paper introduces CottoNet, a lightweight and efficient deep learning framework for detecting early-stage cotton diseases using only RGB images captured by unmanned aerial vehicles (UAVs). The proposed model integrates an EfficientNetV2-S backbone with a Dual-Attention Feature Pyramid Network (DA-FPN) and a novel Early Symptom Emphasis Module (ESEM) to enhance sensitivity to subtle visual cues such as chlorosis, minor lesions, and texture irregularities. A custom-labeled dataset was collected from cotton fields in Uzbekistan to evaluate the model under realistic agricultural conditions. CottoNet achieved a mean average precision (mAP@50) of 89.7%, an F1 score of 88.2%, and an early detection accuracy (EDA) of 91.5%, outperforming existing lightweight models while maintaining real-time inference speed on embedded devices. The results demonstrate that CottoNet offers a scalable, accurate, and field-ready solution for precision agriculture in resource-limited settings.https://www.mdpi.com/2504-446X/9/5/385UAV-based cotton disease detectionchannel attention moduleembedded devicesdual-attention feature pyramid network
spellingShingle Halimjon Khujamatov
Shakhnoza Muksimova
Mirjamol Abdullaev
Jinsoo Cho
Cheolwon Lee
Heung-Seok Jeon
Empowering Smallholder Farmers with UAV-Based Early Cotton Disease Detection Using AI
Drones
UAV-based cotton disease detection
channel attention module
embedded devices
dual-attention feature pyramid network
title Empowering Smallholder Farmers with UAV-Based Early Cotton Disease Detection Using AI
title_full Empowering Smallholder Farmers with UAV-Based Early Cotton Disease Detection Using AI
title_fullStr Empowering Smallholder Farmers with UAV-Based Early Cotton Disease Detection Using AI
title_full_unstemmed Empowering Smallholder Farmers with UAV-Based Early Cotton Disease Detection Using AI
title_short Empowering Smallholder Farmers with UAV-Based Early Cotton Disease Detection Using AI
title_sort empowering smallholder farmers with uav based early cotton disease detection using ai
topic UAV-based cotton disease detection
channel attention module
embedded devices
dual-attention feature pyramid network
url https://www.mdpi.com/2504-446X/9/5/385
work_keys_str_mv AT halimjonkhujamatov empoweringsmallholderfarmerswithuavbasedearlycottondiseasedetectionusingai
AT shakhnozamuksimova empoweringsmallholderfarmerswithuavbasedearlycottondiseasedetectionusingai
AT mirjamolabdullaev empoweringsmallholderfarmerswithuavbasedearlycottondiseasedetectionusingai
AT jinsoocho empoweringsmallholderfarmerswithuavbasedearlycottondiseasedetectionusingai
AT cheolwonlee empoweringsmallholderfarmerswithuavbasedearlycottondiseasedetectionusingai
AT heungseokjeon empoweringsmallholderfarmerswithuavbasedearlycottondiseasedetectionusingai