An End-to-End Two-Phase Deep Learning-Based workflow to Segment Man-made Objects Around Reservoirs

Abstract

Reservoirs are fundamental infrastructures for the management of water resources. Constructions around them can negatively impact their quality. Such unauthorized constructions can be monitored by land cover mapping (LCM) remote sensing (RS) images. In recent years, deep learning (DL) has attracted considerable attention as a method for LCM the RS imagery and has achieved remarkable success. In this paper, we develop a new approach based on DL and image processing techniques for man-made object segmentation around the reservoirs. In order to segment man-made objects around the reservoirs in an end-to-end procedure, segmenting reservoirs and identifying the region of interest (RoI) around them are essential. In the proposed two-phase workflow, the reservoir is initially segmented using a DL model. A post-processing stage is proposed to remove errors such as floating vegetation. Next, the RoI around the reservoir (RoIaR) is identified using the proposed image processing techniques. Finally, the man-made objects in the RoIaR are segmented using a DL architecture. To illustrate the proposed approach, our task of interest is segmenting man-made objects around some of the most important reservoirs in Brazil. Therefore, we trained the proposed workflow using collected Google Earth (GE) images of eight reservoirs in Brazil over two different years. The U-Net-based and SegNet-based architectures are trained to segment the reservoirs. To segment man-made objects in the RoIaR, we trained and evaluated four possible architectures, U-Net, FPN, LinkNet, and PSPNet. Although the collected data has a high diversity (for example, they belong to different states, seasons, resolutions, etc.), we achieved good performances in both phases. The highest achieved F1-score for the test sets of phase-1 and phase-2 semantic segmentation stages are 96.53% and 90.32%, respectively. Furthermore, applying the proposed post-processing to the output of reservoir segmentation improves the precision in all studied reservoirs except two cases. We validated the prepared workflow with a reservoir dataset outside the training reservoirs. The F1-scores of the phase-1 semantic segmentation stage, post-processing stage, and phase-2 semantic segmentation stage are 92.54%, 94.68%, and 88.11%, respectively, which show high generalization ability of the prepared workflow.

Impact of climatic anomalies and reservoir induced seismicity on earthquake generation using Federated Learning

“…(Abdalzaher et al, 2023) employed ML and IoT for generation of early warnings before and occurrence of an earthquake. (Hamidishad & Junior, 2023) applied deep learning methods to study induced seismicity impact caused by artrificial loading by man-made objects. (Scorzini etal, 2023) examined hydrological impact of reservoirs on earthquake generation using deep learning methods.…”

Impact of climatic anomalies and reservoir induced seismicity on earthquake generation using Federated Learning

“…Rainfall, temperature, and pressure being essential atmospheric parameters, have been focused by a large number of studies in the last decade to elaborate their direct or indirect impact on earthquake generation [11]. Recent studies on climate change argue that increase in atmospheric temperature and air pressure along with decreasing rate of rainfall during the past decade, have demonstrated a significant relationship with earthquake generation [12].…”

Two-phase methods to segment man-made objects around reservoirs

“…• Development of an end-to-end workflow for man-made object segmentation around reservoirs. The proposed approach and results are described in Hamidishad and Marcondes Cesar Jr [2023].…”

“…A DL-based approach for man-made object segmentation around reservoirs This chapter content is based on the publication Hamidishad and Marcondes Cesar Jr [2023].…”