Monitoring yellow rust progression during spring critical wheat growth periods using multi‐temporal Sentinel‐2 imagery DOI Open Access
Huiqin Ma, Jingcheng Zhang, Wenjiang Huang

et al.

Pest Management Science, Journal Year: 2024, Volume and Issue: 80(12), P. 6082 - 6095

Published: Aug. 14, 2024

Abstract BACKGROUND Yellow rust ( Puccinia striiformis f. sp. tritici ) is a devastating hazard to wheat production, which poses serious threat yield and food security in the main wheat‐producing areas eastern China. It necessary monitor yellow progression during spring critical growth periods support its prediction by providing timely calibrations for disease models green prevention control. RESULTS Three Sentinel‐2 images three (jointing, heading, filling) were acquired. Spectral, texture, color features all extracted each period disease. Then period‐specific feature sets obtained. Given differences field epidemic status periods, period‐targeted monitoring established map damage track spatiotemporal change. The models' performance was then validated based on truth data (87 jointing period, 183 heading 155 filling period). validation results revealed that representation of our model group realistic credible. overall accuracy healthy diseased pixel classification at reached 87.4%, coefficient determination R 2 index regression 0.77 (heading period) 0.76 (filling model‐group‐result‐based change detection across entire study area proportions conforming expected development pattern jointing‐to‐heading heading‐to‐filling 98.2% 84.4% respectively. CONCLUSIONS Our jointing, overcomes limitations most existing only single‐phase remote sensing information. performs well revealing spring, can update trends optimize management, provide basis correct model. © 2024 Society Chemical Industry.

Language: Английский

Remote Sensing Monitoring of Rice Diseases and Pests from Different Data Sources: A Review DOI Creative Commons
Qiong Zheng, Wenjiang Huang, Qing Xia

et al.

Agronomy, Journal Year: 2023, Volume and Issue: 13(7), P. 1851 - 1851

Published: July 13, 2023

Rice is an important food crop in China, and diseases pests are the main factors threatening its safety, ecology, efficient production. The development of remote sensing technology provides means for non-destructive rapid monitoring that threaten rice crops. This paper aims to provide insights into current future trends monitoring. First, we expound mechanism introduce applications different commonly data sources (hyperspectral data, multispectral thermal infrared fluorescence, multi-source fusion) pests. Secondly, summarize methods pests, including statistical discriminant type, machine learning, deep learning algorithm. Finally, a general framework facilitate or which ideas technical guidance unknown point out challenges directions disease pest work new references subsequent using sensing.

Language: Английский

Citations

30
Deep Learning Analysis of Rice Blast Disease Using Remote Sensing Images DOI
Shubhajyoti Das, Arindam Biswas,

C Vimalkumar

et al.

IEEE Geoscience and Remote Sensing Letters, Journal Year: 2023, Volume and Issue: 20, P. 1 - 5

Published: Jan. 1, 2023

Large-scale agricultural production systems require disease monitoring and pest management on a real-time basis. Monitoring phenology is one of the possible ways to save products from huge yield loss incurred due diseases. Rice major food crops across globe. Leaf blast in rice affects its productivity all over world. leaf essential for strategic tactical decisions. Conventional methods large-scale are laborious, time taking, above all, suffer inaccuracy. Remote sensing parameters useful diseases crop health large scale. Spectral indices derived remote data provide characteristic features distinguish areas between healthy infected facilitating application. Assessment incidence based land surface temperature moderate resolution imaging spectroradiometer (MODIS) spectral normalized difference vegetation index (NDVI), enhanced (EVI), moisture (NDMI), soil adjusted (SAVI), stress (Sentinel-2) have been used predict patterns. A deep learning-based model developed assess condition at field The provided 90.02% training accuracy 85.33% validation accuracy. learning images could occurrence real time.

Language: Английский

Citations

29
Early Detection of Rice Leaf Blast Disease Using Unmanned Aerial Vehicle Remote Sensing: A Novel Approach Integrating a New Spectral Vegetation Index and Machine Learning DOI Creative Commons
Dongxue Zhao, Yingli Cao, Jinpeng Li

et al.

Agronomy, Journal Year: 2024, Volume and Issue: 14(3), P. 602 - 602

Published: March 17, 2024

Leaf blast is recognized as one of the most devastating diseases affecting rice production in world, seriously threatening yield. Therefore, early detection leaf extremely important to limit spread and propagation disease. In this study, a blast-specific spectral vegetation index RBVI = 9.78R816−R724 − 2.08(ρ736/R724) was designed qualitatively detect level disease canopy field improve accuracy by remote sensing unmanned aerial vehicle. Stacking integrated learning, AdaBoost, SVM were used compare analyze performance traditional for blast. The results showed that stacking model constructed based on had highest (OA: 95.9%, Kappa: 93.8%). Compared stacking, AdaBoost models slightly degraded. with conventional SVIs, higher its ability field. proposed study can more effectively UAV make up shortcomings hyperspectral detection, which susceptible interference environmental factors. provide simple effective method management timely control

Language: Английский

Citations

9
A lightweight model for early perception of rice diseases driven by photothermal information fusion DOI
Ning Yang, Chen Liang, Tongge Li

et al.

Computers and Electronics in Agriculture, Journal Year: 2025, Volume and Issue: 233, P. 110150 - 110150

Published: Feb. 24, 2025

Language: Английский

Citations

1
Quantifying effect of maize tassels on LAI estimation based on multispectral imagery and machine learning methods DOI
Mingchao Shao, Chenwei Nie, Aijun Zhang

et al.

Computers and Electronics in Agriculture, Journal Year: 2023, Volume and Issue: 211, P. 108029 - 108029

Published: July 13, 2023

Language: Английский

Citations

18
Dual sampling linear regression ensemble to predict wheat yield across growing seasons with hyperspectral sensing DOI
Shuaipeng Fei, Shunfu Xiao,

Jinyu Zhu

et al.

Computers and Electronics in Agriculture, Journal Year: 2023, Volume and Issue: 216, P. 108514 - 108514

Published: Dec. 11, 2023

Language: Английский

Citations

11
Monitoring of winter wheat stripe rust by collaborating canopy SIF with wavelet energy coefficients DOI Creative Commons

Kehui Ren,

Yingying Dong, Wenjiang Huang

et al.

Computers and Electronics in Agriculture, Journal Year: 2023, Volume and Issue: 215, P. 108366 - 108366

Published: Nov. 11, 2023

Stripe rust has caused tremendous damage to wheat quality and production. Disease-specific factors revealing group structure photosynthetic physiology contribute high-precision monitoring for stripe rust. In this study, we proposed a remote sensing model that collaborates wavelet features (WFs) solar-induced chlorophyll fluorescence (SIF). First, sensitive including vegetation indices (VIs), SIF parameters, WFs, fractional-order derivative spectra (FODs) were screened based on correlation coefficient (CC) analysis variable importance in projection (VIP). Then, through collaboration among features, six feature sets received imported partial least squares regression (PLSR), back-propagation neural network (BPNN), random forest (RF), extreme gradient boosting (XGBoost). Finally, models was evaluated two methods: holdout cross-validation 5-fold cross validation ascertain the optimal feature-algorithm combination. The results demonstrated of canopy with any markedly improved accuracy due its responsive nature plant's physiology. XGBoost WFs-SIF as input achieved accuracy, at 16.6% increase R2 32.4% reduction RMSE compared VIs-PLSR model. Correlation evaluation indexes (R2 RMSE) under methods showed determination coefficients 0.743 0.837, indicating mutual high reliability conclusions. This study suggests between WFs exhibits considerable feasibility rust, providing novel insight future field-scale diagnosis crop diseases.

Language: Английский

Citations

10
Hyperspectral classification of ancient cultural remains using machine learning DOI

Rongji Luo,

Peng Lü, Panpan Chen

et al.

Remote Sensing Applications Society and Environment, Journal Year: 2025, Volume and Issue: unknown, P. 101457 - 101457

Published: Jan. 1, 2025

Language: Английский

Citations

0
Evaluating the potential of airborne hyperspectral imagery in monitoring common beans with common bacterial blight at different infection stages DOI

Binghan Jing,

Jiachen Wang, Xin Zhang

et al.

Biosystems Engineering, Journal Year: 2025, Volume and Issue: 251, P. 145 - 158

Published: Feb. 17, 2025

Language: Английский

Citations

0
A LAMP Detection System Based on a Microfluidic Chip for Pyricularia grisea DOI Creative Commons
Chenwei Wu,

Jianing Cheng,

Yinchao Zhang

et al.

Sensors, Journal Year: 2025, Volume and Issue: 25(8), P. 2511 - 2511

Published: April 16, 2025

As one of the major rice fungal diseases, blast poses a serious threat to yield and quality globally. It is caused by pathogen Pyricularia grisea. Therefore, development rapid, accurate, portable microfluidic detection system for grisea important control blast. This study presents an integrated rapid sensitive using LAMP method. The includes chip, temperature module, OpenMv camera. micro-mixing channels with shear structures improve mixing efficiency about 98%. Flow-blocking valves are used reduce reagent loss in reaction chamber. module heat chamber, maintaining stable 65 °C. chip chamber image inspection developed can detect range 10 copies/μL–105 copies/μL within 45 min. Specificity interference experiments were performed on grisea, validating method’s good reliability. based has strong potential early effective

Language: Английский

Citations

0