Bathymetric mapping and estimation of water storage in a shallow lake using a remote sensing inversion method based on machine learning

Accurate lake depth mapping and estimation of changes in water level and water storage are fundamental significance for understanding the lake water resources on the Tibetan Plateau. In this study, combined with satellite images and bathymetric data, we comprehensively evaluate the accuracy of a multi-factor combined linear regression model (MLR) and machine learning models, create a depth distribution map and compare it with the spatial interpolation, and estimate the change of water level and water storage based on the inverted depth. The results indicated that the precision of the random forest (RF) was the highest with a coefficient of determination (R (2)) value (0.9311) and mean absolute error (MAE) values (1.13 m) in the test dataset and had high reliability in the overall depth distribution. The water level increased by 9.36 m at a rate of 0.47 m/y, and the water storage increased by 1.811 km(3) from 1998 to 2018 based on inversion depth. The water level change was consistent with that of the Shuttle Radar Topography Mission (SRTM) method. Our work shows that this method may be employed to study the water depth distribution and its changes by combining with bathymetric data and satellite imagery in shallow lakes.

Automated summary

In this study, accurate lake depth mapping and estimation of water level changes and water storage on the Tibetan Plateau were achieved through the use of a multi-factor combined linear regression model and machine learning models with satellite images and bathymetric data. The random forest model showed the highest precision and reliability, with consistent water level changes compared to the Shuttle Radar Topography Mission method. This method can be utilized for studying water depth distribution and changes in shallow lakes when combined with bathymetric data and satellite imagery.