Enhanced Crop Leaf Area Index Estimation via Random Forest Regression: Bayesian Optimization and Feature Selection Approach

The Leaf Area Index (LAI) is a crucial structural parameter linked to the photosynthetic capacity and biomass of crops. While integrating machine learning algorithms with spectral variables has improved LAI estimation over large areas, excessive input parameters can lead to data redundancy and reduc...

Full description

Saved in:
Bibliographic Details
Main Authors: Jun Zhang, Jinpeng Cheng, Cuiping Liu, Qiang Wu, Shuping Xiong, Hao Yang, Shenglong Chang, Yuanyuan Fu, Mohan Yang, Shiyu Zhang, Guijun Yang, Xinming Ma
Format: Article
Language:English
Published: MDPI AG 2024-10-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/16/21/3917
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846173200618094592
author Jun Zhang
Jinpeng Cheng
Cuiping Liu
Qiang Wu
Shuping Xiong
Hao Yang
Shenglong Chang
Yuanyuan Fu
Mohan Yang
Shiyu Zhang
Guijun Yang
Xinming Ma
author_facet Jun Zhang
Jinpeng Cheng
Cuiping Liu
Qiang Wu
Shuping Xiong
Hao Yang
Shenglong Chang
Yuanyuan Fu
Mohan Yang
Shiyu Zhang
Guijun Yang
Xinming Ma
author_sort Jun Zhang
collection DOAJ
description The Leaf Area Index (LAI) is a crucial structural parameter linked to the photosynthetic capacity and biomass of crops. While integrating machine learning algorithms with spectral variables has improved LAI estimation over large areas, excessive input parameters can lead to data redundancy and reduced generalizability across different crop species. To address these challenges, we propose a novel framework based on Bayesian-Optimized Random Forest Regression (Bayes-RFR) for enhanced LAI estimation. This framework employs a tree model-based feature selection method to identify critical features, reducing redundancy and improving model interpretability. A Gaussian process serves as a prior model to optimize the hyperparameters of the Random Forest Regression. The field experiments conducted over two years on maize and wheat involved collecting LAI, hyperspectral, multispectral, and RGB data. The results indicate that the tree model-based feature selection outperformed the traditional correlation analysis and Recursive Feature Elimination (RFE). The Bayes-RFR model demonstrated a superior validation accuracy compared to the standard Random Forest Regression and Pso-optimized models, with the R<sup>2</sup> values increasing by 27% for the maize hyperspectral data, 12% for the maize multispectral data, and 47% for the wheat hyperspectral data. These findings suggest that the proposed Bayes-RFR framework significantly enhances the stability and predictive capability of LAI estimation across various crop types, offering valuable insights for precision agriculture and crop monitoring.
format Article
id doaj-art-d7ca854d7ea74fec8cc5e1bf6de044b2
institution Kabale University
issn 2072-4292
language English
publishDate 2024-10-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-d7ca854d7ea74fec8cc5e1bf6de044b22024-11-08T14:40:12ZengMDPI AGRemote Sensing2072-42922024-10-011621391710.3390/rs16213917Enhanced Crop Leaf Area Index Estimation via Random Forest Regression: Bayesian Optimization and Feature Selection ApproachJun Zhang0Jinpeng Cheng1Cuiping Liu2Qiang Wu3Shuping Xiong4Hao Yang5Shenglong Chang6Yuanyuan Fu7Mohan Yang8Shiyu Zhang9Guijun Yang10Xinming Ma11College of Agronomy, Henan Agricultural University, Zhengzhou 450046, ChinaCollege of Agronomy, Henan Agricultural University, Zhengzhou 450046, ChinaCollege of Agronomy, Henan Agricultural University, Zhengzhou 450046, ChinaCollege of Agronomy, Henan Agricultural University, Zhengzhou 450046, ChinaCollege of Agronomy, Henan Agricultural University, Zhengzhou 450046, ChinaKey Laboratory of Quantitative Remote Sensing in Agriculture of Ministry of Agriculture and Rural Affairs, Information Technology Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097, ChinaCollege of Software, Henan Normal University, Xinxiang 453000, ChinaCollege of Information and Management Science, Henan Agricultural University, Zhengzhou 450002, ChinaCollege of Agronomy, Henan Agricultural University, Zhengzhou 450046, ChinaCollege of Agronomy, Henan Agricultural University, Zhengzhou 450046, ChinaKey Laboratory of Quantitative Remote Sensing in Agriculture of Ministry of Agriculture and Rural Affairs, Information Technology Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097, ChinaCollege of Agronomy, Henan Agricultural University, Zhengzhou 450046, ChinaThe Leaf Area Index (LAI) is a crucial structural parameter linked to the photosynthetic capacity and biomass of crops. While integrating machine learning algorithms with spectral variables has improved LAI estimation over large areas, excessive input parameters can lead to data redundancy and reduced generalizability across different crop species. To address these challenges, we propose a novel framework based on Bayesian-Optimized Random Forest Regression (Bayes-RFR) for enhanced LAI estimation. This framework employs a tree model-based feature selection method to identify critical features, reducing redundancy and improving model interpretability. A Gaussian process serves as a prior model to optimize the hyperparameters of the Random Forest Regression. The field experiments conducted over two years on maize and wheat involved collecting LAI, hyperspectral, multispectral, and RGB data. The results indicate that the tree model-based feature selection outperformed the traditional correlation analysis and Recursive Feature Elimination (RFE). The Bayes-RFR model demonstrated a superior validation accuracy compared to the standard Random Forest Regression and Pso-optimized models, with the R<sup>2</sup> values increasing by 27% for the maize hyperspectral data, 12% for the maize multispectral data, and 47% for the wheat hyperspectral data. These findings suggest that the proposed Bayes-RFR framework significantly enhances the stability and predictive capability of LAI estimation across various crop types, offering valuable insights for precision agriculture and crop monitoring.https://www.mdpi.com/2072-4292/16/21/3917leaf area indexhyperparameter optimizationBayesian algorithmrandom forests
spellingShingle Jun Zhang
Jinpeng Cheng
Cuiping Liu
Qiang Wu
Shuping Xiong
Hao Yang
Shenglong Chang
Yuanyuan Fu
Mohan Yang
Shiyu Zhang
Guijun Yang
Xinming Ma
Enhanced Crop Leaf Area Index Estimation via Random Forest Regression: Bayesian Optimization and Feature Selection Approach
Remote Sensing
leaf area index
hyperparameter optimization
Bayesian algorithm
random forests
title Enhanced Crop Leaf Area Index Estimation via Random Forest Regression: Bayesian Optimization and Feature Selection Approach
title_full Enhanced Crop Leaf Area Index Estimation via Random Forest Regression: Bayesian Optimization and Feature Selection Approach
title_fullStr Enhanced Crop Leaf Area Index Estimation via Random Forest Regression: Bayesian Optimization and Feature Selection Approach
title_full_unstemmed Enhanced Crop Leaf Area Index Estimation via Random Forest Regression: Bayesian Optimization and Feature Selection Approach
title_short Enhanced Crop Leaf Area Index Estimation via Random Forest Regression: Bayesian Optimization and Feature Selection Approach
title_sort enhanced crop leaf area index estimation via random forest regression bayesian optimization and feature selection approach
topic leaf area index
hyperparameter optimization
Bayesian algorithm
random forests
url https://www.mdpi.com/2072-4292/16/21/3917
work_keys_str_mv AT junzhang enhancedcropleafareaindexestimationviarandomforestregressionbayesianoptimizationandfeatureselectionapproach
AT jinpengcheng enhancedcropleafareaindexestimationviarandomforestregressionbayesianoptimizationandfeatureselectionapproach
AT cuipingliu enhancedcropleafareaindexestimationviarandomforestregressionbayesianoptimizationandfeatureselectionapproach
AT qiangwu enhancedcropleafareaindexestimationviarandomforestregressionbayesianoptimizationandfeatureselectionapproach
AT shupingxiong enhancedcropleafareaindexestimationviarandomforestregressionbayesianoptimizationandfeatureselectionapproach
AT haoyang enhancedcropleafareaindexestimationviarandomforestregressionbayesianoptimizationandfeatureselectionapproach
AT shenglongchang enhancedcropleafareaindexestimationviarandomforestregressionbayesianoptimizationandfeatureselectionapproach
AT yuanyuanfu enhancedcropleafareaindexestimationviarandomforestregressionbayesianoptimizationandfeatureselectionapproach
AT mohanyang enhancedcropleafareaindexestimationviarandomforestregressionbayesianoptimizationandfeatureselectionapproach
AT shiyuzhang enhancedcropleafareaindexestimationviarandomforestregressionbayesianoptimizationandfeatureselectionapproach
AT guijunyang enhancedcropleafareaindexestimationviarandomforestregressionbayesianoptimizationandfeatureselectionapproach
AT xinmingma enhancedcropleafareaindexestimationviarandomforestregressionbayesianoptimizationandfeatureselectionapproach