Remote Sensing-Based Multilayer Perceptron Model for Grassland Above-Ground Biomass Estimation

Above-ground biomass (AGB) is a core indicator for evaluating grassland ecosystem health and carbon storage. Traditional ground-based AGB measurements are labor-intensive and ill suited for large-scale monitoring. This study addresses this gap by developing a Multilayer Perceptron (MLP) model integr...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhiguo Wang, Shuai Ma, Yongguang Zhai, Pingping Huang, Xiangli Yang, Jianhao Cui, Qimuge Eridun
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/11/6280
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850129575479083008
author Zhiguo Wang
Shuai Ma
Yongguang Zhai
Pingping Huang
Xiangli Yang
Jianhao Cui
Qimuge Eridun
author_facet Zhiguo Wang
Shuai Ma
Yongguang Zhai
Pingping Huang
Xiangli Yang
Jianhao Cui
Qimuge Eridun
author_sort Zhiguo Wang
collection DOAJ
description Above-ground biomass (AGB) is a core indicator for evaluating grassland ecosystem health and carbon storage. Traditional ground-based AGB measurements are labor-intensive and ill suited for large-scale monitoring. This study addresses this gap by developing a Multilayer Perceptron (MLP) model integrating Landsat 9 OLI/TIRS imagery acquired on 15 August 2024, with ground data from 78 sampling points (62 training, 16 testing). Incorporating fourteen multi-source features (seven vegetation indices, e.g., Modified Vegetation Index (MVI) and Green Chlorophyll Index (CIg); four meteorological variables; three soil properties), all data were standardized via z-score normalization before training. The MLP model, optimized via six-fold cross-validation, achieved an R<sup>2</sup> of 0.765 and RMSE of 38.066 g/m<sup>2</sup>, outperforming XGBoost (R<sup>2</sup> = 0.723, RMSE = 41.354 g/m<sup>2</sup>) with a statistically significant 5.8% accuracy improvement (<i>p</i> < 0.05). Spatial analysis revealed a north-to-south AGB gradient, strongly correlated with precipitation gradients (250–350 mm/year) and soil organic carbon (R = 0.428). These findings provide a robust framework for climate-adaptive grassland management and carbon assessment in semi-arid regions.
format Article
id doaj-art-462bf8f491944f349319dc7fb8afa92b
institution OA Journals
issn 2076-3417
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-462bf8f491944f349319dc7fb8afa92b2025-08-20T02:32:56ZengMDPI AGApplied Sciences2076-34172025-06-011511628010.3390/app15116280Remote Sensing-Based Multilayer Perceptron Model for Grassland Above-Ground Biomass EstimationZhiguo Wang0Shuai Ma1Yongguang Zhai2Pingping Huang3Xiangli Yang4Jianhao Cui5Qimuge Eridun6College of Information Engineering, Inner Mongolia University of Technology, Hohhot 010080, ChinaCollege of Information Engineering, Inner Mongolia University of Technology, Hohhot 010080, ChinaCollege of Information Engineering, Inner Mongolia University of Technology, Hohhot 010080, ChinaCollege of Information Engineering, Inner Mongolia University of Technology, Hohhot 010080, ChinaCollege of Information Science and Engineering, Chongqing Jiaotong University, Chongqing 400074, ChinaCollege of Information Engineering, Inner Mongolia University of Technology, Hohhot 010080, ChinaGrassland Workstation, Xiwuzhumuqin Banner, Xilingol League 026200, ChinaAbove-ground biomass (AGB) is a core indicator for evaluating grassland ecosystem health and carbon storage. Traditional ground-based AGB measurements are labor-intensive and ill suited for large-scale monitoring. This study addresses this gap by developing a Multilayer Perceptron (MLP) model integrating Landsat 9 OLI/TIRS imagery acquired on 15 August 2024, with ground data from 78 sampling points (62 training, 16 testing). Incorporating fourteen multi-source features (seven vegetation indices, e.g., Modified Vegetation Index (MVI) and Green Chlorophyll Index (CIg); four meteorological variables; three soil properties), all data were standardized via z-score normalization before training. The MLP model, optimized via six-fold cross-validation, achieved an R<sup>2</sup> of 0.765 and RMSE of 38.066 g/m<sup>2</sup>, outperforming XGBoost (R<sup>2</sup> = 0.723, RMSE = 41.354 g/m<sup>2</sup>) with a statistically significant 5.8% accuracy improvement (<i>p</i> < 0.05). Spatial analysis revealed a north-to-south AGB gradient, strongly correlated with precipitation gradients (250–350 mm/year) and soil organic carbon (R = 0.428). These findings provide a robust framework for climate-adaptive grassland management and carbon assessment in semi-arid regions.https://www.mdpi.com/2076-3417/15/11/6280above-ground biomassmultilayer perceptronremote sensinggrasslandsmachine learning
spellingShingle Zhiguo Wang
Shuai Ma
Yongguang Zhai
Pingping Huang
Xiangli Yang
Jianhao Cui
Qimuge Eridun
Remote Sensing-Based Multilayer Perceptron Model for Grassland Above-Ground Biomass Estimation
Applied Sciences
above-ground biomass
multilayer perceptron
remote sensing
grasslands
machine learning
title Remote Sensing-Based Multilayer Perceptron Model for Grassland Above-Ground Biomass Estimation
title_full Remote Sensing-Based Multilayer Perceptron Model for Grassland Above-Ground Biomass Estimation
title_fullStr Remote Sensing-Based Multilayer Perceptron Model for Grassland Above-Ground Biomass Estimation
title_full_unstemmed Remote Sensing-Based Multilayer Perceptron Model for Grassland Above-Ground Biomass Estimation
title_short Remote Sensing-Based Multilayer Perceptron Model for Grassland Above-Ground Biomass Estimation
title_sort remote sensing based multilayer perceptron model for grassland above ground biomass estimation
topic above-ground biomass
multilayer perceptron
remote sensing
grasslands
machine learning
url https://www.mdpi.com/2076-3417/15/11/6280
work_keys_str_mv AT zhiguowang remotesensingbasedmultilayerperceptronmodelforgrasslandabovegroundbiomassestimation
AT shuaima remotesensingbasedmultilayerperceptronmodelforgrasslandabovegroundbiomassestimation
AT yongguangzhai remotesensingbasedmultilayerperceptronmodelforgrasslandabovegroundbiomassestimation
AT pingpinghuang remotesensingbasedmultilayerperceptronmodelforgrasslandabovegroundbiomassestimation
AT xiangliyang remotesensingbasedmultilayerperceptronmodelforgrasslandabovegroundbiomassestimation
AT jianhaocui remotesensingbasedmultilayerperceptronmodelforgrasslandabovegroundbiomassestimation
AT qimugeeridun remotesensingbasedmultilayerperceptronmodelforgrasslandabovegroundbiomassestimation