Modeling soil respiration in summer maize cropland based on hyperspectral imagery and machine learning

被引:0
作者
Zeng, Fanchao [1 ,2 ]
Sun, Jinwei [3 ]
Zhang, Huihui [1 ]
Yang, Lizhen [1 ]
Zhao, Xiaoxue [1 ]
Zhao, Jing [4 ]
Bo, Xiaodong [1 ]
Cao, Yuxin [1 ]
Yao, Fuqi [1 ]
Yuan, Fenghui [2 ,5 ]
机构
[1] Ludong Univ, Sch Hydraul & Civil Engn, Yantai, Peoples R China
[2] Chinese Acad Sci, Northeast Inst Geog & Agroecol, State Key Lab Black Soils Conservat & Utilizat, Changchun, Peoples R China
[3] Ludong Univ, Sch Resources & Environm Engn, Yantai, Peoples R China
[4] Changjiang Water Resources Commiss, Changjiang River Sci Res Inst, Wuhan, Peoples R China
[5] Univ Minnesota, Dept Soil Water & Climate, St Paul, MN 55105 USA
基金
中国国家自然科学基金;
关键词
machine learning; soil respiration; maize; soil temperature; hyperspectral image; CARBON SEQUESTRATION; SPECTRAL REFLECTANCE; CHLOROPHYLL CONTENT; FOREST; VEGETATION; TEMPERATE; ALGORITHMS; NITROGEN; LEAVES;
D O I
10.3389/fenvs.2024.1505987
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Introduction Soil respiration (SR), the release of carbon dioxide (CO2) from soil due to the decomposition of organic matter and root respiration, is an important indicator for understanding agricultural carbon cycling and assessing anthropogenic impacts on the environment. Hyperspectral remote sensing offers a potential rapid, non-destructive approach for monitoring in agriculture. However, it remains uncertain whether hyperspectral remote sensing can provide an accurate and efficient method for estimating SR rate in croplands, particularly across different maize growth stages of under varying drought conditions.Methods In the study, we investigated the potential of combining hyperspectral remote sensing data with machine learning model (ML) to quantify SR rate in croplands. A drought field experiment was conducted, and SR and hyperspectral imagery were collected during four maize growth stages: Jointing Stage (JS), Tasseling Stage (TS), Flowering Stage (FS), and Grain Filling Stage (GFS). We compared the performance of traditional multiple linear regression (MLR) with that of an ML model (extreme gradient boosting, XGBoost), in simulating SR rate across these four growth stages.Results Our findings demonstrated that the simulation of the XGBoost model, utilizing soil temperature ( T s ) and hyperspectral data, outperformed the MLR model. Across different growth stages, the SR simulated by the XGBoost model (R 2 = 0.8103) was more reliable than that of the MLR model (R 2 = 0.7451). The XGBoost model can also effectively capture the impact of drought treatments on SR.Discussion The XGBoost model's tree-based structure allows it to effectively capture complex interactions and nonlinear patterns within variables, while its high sensitivity to changes in SR rates under drought conditions makes it more reliable for modeling SR across different growth stages compared to the linear-based MLR model. This study highlights the great promise of ML combined with hyperspectral imaging in predicting SR rate in croplands, which will help guide future agricultural management and environmental informatics.
引用
收藏
页数:13
相关论文
共 50 条
[41]   Monitoring of Soil Moisture Content of Winter Oilseed Rape (Brassica napus L.) Based on Hyperspectral and Machine Learning Models [J].
Tang, Zijun ;
Zhang, Wei ;
Xiang, Youzhen ;
Liu, Xiaochi ;
Wang, Xin ;
Shi, Hongzhao ;
Li, Zhijun ;
Zhang, Fucang .
JOURNAL OF SOIL SCIENCE AND PLANT NUTRITION, 2024, 24 (01) :1250-1260
[42]   Estimation Model of Rice Aboveground Dry Biomass Based on the Machine Learning and Hyperspectral Characteristic Parameters of the Canopy [J].
Wang, Xiaoke ;
Xu, Guiling ;
Feng, Yuehua ;
Peng, Jinfeng ;
Gao, Yuqi ;
Li, Jie ;
Han, Zhili ;
Luo, Qiangxin ;
Ren, Hongjun ;
You, Xiaoxuan ;
Lu, Wei .
AGRONOMY-BASEL, 2023, 13 (07)
[43]   Comparing machine learning-derived global estimates of soil respiration and its components with those from terrestrial ecosystem models [J].
Lu, Haibo ;
Li, Shihua ;
Ma, Minna ;
Bastrikov, Vladislav ;
Chen, Xiuzhi ;
Ciais, Philippe ;
Dai, Yongjiu ;
Ito, Akihiko ;
Ju, Weimin ;
Lienert, Sebastian ;
Lombardozzi, Danica ;
Lu, Xingjie ;
Maignan, Fabienne ;
Nakhavali, Mahdi ;
Quine, Timothy ;
Schindlbacher, Andreas ;
Wang, Jun ;
Wang, Yingping ;
Warlind, David ;
Zhang, Shupeng ;
Yuan, Wenping .
ENVIRONMENTAL RESEARCH LETTERS, 2021, 16 (05)
[44]   Toward Automated Machine Learning-Based Hyperspectral Image Analysis in Crop Yield and Biomass Estimation [J].
Li, Kai-Yun ;
Sampaio de Lima, Raul ;
Burnside, Niall G. ;
Vahtmaee, Ele ;
Kutser, Tiit ;
Sepp, Karli ;
Cabral Pinheiro, Victor Henrique ;
Yang, Ming-Der ;
Vain, Ants ;
Sepp, Kalev .
REMOTE SENSING, 2022, 14 (05)
[45]   Soil respiration dynamics and effects of hydrothermal factors and NPP during growing period of maize cropland ecosystem in Songnen Plain, China [J].
Gao, Yonggang ;
Chu, Zheng ;
Jiang, Lanqi ;
Zhou, Yongji ;
Zhao, Fang ;
Gao, Feng ;
Liu, Dan ;
Zhao, Huiying .
TROPICAL ECOLOGY, 2025, 66 (01) :55-66
[46]   Retrieval of Hyperspectral Surface Reflectance Based on Machine Learning [J].
Zhu, Sijie ;
Lei, Bin ;
Wu, Yirong .
REMOTE SENSING, 2018, 10 (02)
[47]   Hyperspectral Anomaly Detection Based on Machine Learning: An Overview [J].
Xu, Yichu ;
Zhang, Lefei ;
Du, Bo ;
Zhang, Liangpei .
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2022, 15 :3351-3364
[48]   Appraisal of EnMAP hyperspectral imagery use in LULC mapping when combined with machine learning pixel-based classifiers [J].
Lekka, Christina ;
Petropoulos, George P. ;
Detsikas, Spyridon E. .
ENVIRONMENTAL MODELLING & SOFTWARE, 2024, 173
[49]   Subspace-based multitask learning framework for hyperspectral imagery classification [J].
Haoyang Yu ;
Lianru Gao ;
Jun Li ;
Bing Zhang .
Multimedia Tools and Applications, 2020, 79 :8887-8909
[50]   Subspace-based multitask learning framework for hyperspectral imagery classification [J].
Yu, Haoyang ;
Gao, Lianru ;
Li, Jun ;
Zhan, Bing .
MULTIMEDIA TOOLS AND APPLICATIONS, 2020, 79 (13-14) :8887-8909