Work

Monte Carlo Deep Learning Model for Quantitative Inversion of Total Nitrogen Concentration in the Source Area of the Yellow River Using Google Earth Engine

Year: 2025

Type: article

Abstract: As a vital ecological barrier in China, the Yellow River source area's water changes significantly impact the regional environment. Traditional remote sensing inversion methods face challenges like limited accuracy and complex data processing. This study uses Sentinel-2 remote sensing data and ground-based hyperspectral data, combined with an improved deep learning model (MC-DL), to establish an efficient framework for key water parameter inversion. Focusing on Ruoergai County, the MC-DL model, enhanced by Monte Carlo dropout, quantitatively inverts total nitrogen (TN) concentration. The MC-DL model outperforms Support Vector Regression (SVR) and Convolutional Neural Network (CNN) in accuracy and stability (R² = 0.95, MAE = 0.08, MBE = -0.004, RMSE = 0.13).This study provides a new technological approach for water monitoring in the Yellow River source area and supports ecological management and protection.

Source: Geoscience and Remote Sensing

DOI: 10.23977/geors.2025.080104

Authors: Ruichun Chang, Chi Zhang, Jian Xu, Zhe Chen, Wanquan Tuo

Institutions: Chengdu University of Technology, Institute of Earth Environment, State Key Laboratory of Loess and Quaternary Geology

Language: English

Topic: Water Quality Monitoring and Analysis

Subfield: Waste Management and Disposal

Field: Environmental Science

Domain: Physical Sciences

SDGs: Clean water and sanitation, Climate action

Open Access status: diamond

Funders: Institute of Earth Environment, Chinese Academy of Sciences, State Key Laboratory of Loess and Quaternary Geology