Neuroevolution deep learning architecture search for estimation of river surface elevation from photogrammetric Digital Surface Models

TL;DR

This paper introduces a novel neuroevolution-based deep learning approach to estimate river surface elevation from photogrammetric DSMs, improving accuracy and automating water level measurements crucial for hydrological modeling and flood prediction.

Contribution

It presents the first dataset specifically created for this task and applies neuroevolution to optimize deep learning architectures for estimating water surface elevation from disturbed DSM data.

Findings

Achieved higher accuracy than manual methods

Demonstrated effectiveness of neuroevolution in architecture search

Enabled automated, high-resolution water surface level estimation

Abstract

Development of the new methods of surface water observation is crucial in the perspective of increasingly frequent extreme hydrological events related to global warming and increasing demand for water. Orthophotos and digital surface models (DSMs) obtained using UAV photogrammetry can be used to determine the Water Surface Elevation (WSE) of a river. However, this task is difficult due to disturbances of the water surface on DSMs caused by limitations of photogrammetric algorithms. In this study, machine learning was used to extract a WSE value from disturbed photogrammetric data. A brand new dataset has been prepared specifically for this purpose by hydrology and photogrammetry experts. The new method is an important step toward automating water surface level measurements with high spatial and temporal resolution. Such data can be used to validate and calibrate of hydrological, hydraulic and hydrodynamic models making hydrological forecasts more accurate, in particular predicting extreme and dangerous events such as floods or droughts. For our knowledge this is the first approach in which dataset was created for this purpose and deep learning models were used for this task. Additionally, neuroevolution algorithm was set to explore different architectures to find local optimal models and non-gradient search was performed to fine-tune the model parameters. The achieved results have better accuracy compared to manual methods of determining WSE from photogrammetric DSMs.