Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

SEN12-WATER: A New Dataset for Hydrological Applications and its Benchmarking

Luigi Russo, Francesco Mauro, Alessandro Sebastianelli, Paolo Gamba, Silvia Liberata Ullo

Abstract

Climate change and increasing droughts pose significant challenges to water resource management around the world. These problems lead to severe water shortages that threaten ecosystems, agriculture, and human communities. To advance the fight against these challenges, we present a new dataset, SEN12-WATER, along with a benchmark using a novel end-to-end Deep Learning (DL) framework for proactive drought-related analysis. The dataset, identified as a spatiotemporal datacube, integrates SAR polarization, elevation, slope, and multispectral optical bands. Our DL framework enables the analysis and estimation of water losses over time in reservoirs of interest, revealing significant insights into water dynamics for drought analysis by examining temporal changes in physical quantities such as water volume. Our methodology takes advantage of the multitemporal and multimodal characteristics of the proposed dataset, enabling robust generalization and advancing understanding of drought, contributing to climate change resilience and sustainable water resource management. The proposed framework involves, among the several components, speckle noise removal from SAR data, a water body segmentation through a U-Net architecture, the time series analysis, and the predictive capability of a Time-Distributed-Convolutional Neural Network (TD-CNN). Results are validated through ground truth data acquired on-ground via dedicated sensors and (tailored) metrics, such as Precision, Recall, Intersection over Union, Mean Squared Error, Structural Similarity Index Measure and Peak Signal-to-Noise Ratio.

SEN12-WATER: A New Dataset for Hydrological Applications and its Benchmarking

Abstract

Climate change and increasing droughts pose significant challenges to water resource management around the world. These problems lead to severe water shortages that threaten ecosystems, agriculture, and human communities. To advance the fight against these challenges, we present a new dataset, SEN12-WATER, along with a benchmark using a novel end-to-end Deep Learning (DL) framework for proactive drought-related analysis. The dataset, identified as a spatiotemporal datacube, integrates SAR polarization, elevation, slope, and multispectral optical bands. Our DL framework enables the analysis and estimation of water losses over time in reservoirs of interest, revealing significant insights into water dynamics for drought analysis by examining temporal changes in physical quantities such as water volume. Our methodology takes advantage of the multitemporal and multimodal characteristics of the proposed dataset, enabling robust generalization and advancing understanding of drought, contributing to climate change resilience and sustainable water resource management. The proposed framework involves, among the several components, speckle noise removal from SAR data, a water body segmentation through a U-Net architecture, the time series analysis, and the predictive capability of a Time-Distributed-Convolutional Neural Network (TD-CNN). Results are validated through ground truth data acquired on-ground via dedicated sensors and (tailored) metrics, such as Precision, Recall, Intersection over Union, Mean Squared Error, Structural Similarity Index Measure and Peak Signal-to-Noise Ratio.
Paper Structure (16 sections, 3 equations, 5 figures, 6 tables)

This paper contains 16 sections, 3 equations, 5 figures, 6 tables.

Table of Contents

  1. Introduction
  2. Related works
  3. Data
  4. Methods
  5. Pre-processing
  6. Segmentation
  7. Next-frame prediction task
  8. Time-series analysis
  9. Results
  10. Results for Segmentation
  11. Ablation study
  12. Results for Next-Frame Prediction
  13. Results for time-series analysis
  14. Discussion
  15. Conclusion
  16. ...and 1 more sections

Figures (5)

  • Figure 1: Visualization of the SEN12-WATER Dataset. On the y-axis are different geographical locations, and on the x-axis are the time series images for each location. Each cube plot shows the compound product of the S1 polarizations (VV+VH) and S2 spectral bands (R+G+B+NIR). The datacube is finally enriched with slope and elevation information for each geolocation. This plot has been produced using https://alessandrosebastianelli.github.io/opensv/pyosv.html.
  • Figure 2: Proposed end-to-end framework and methodology composed of several blocks: segmentation of water basins, prediction of future water and drought masks and evaluation of the quantity of water pixels within each segmented mask.
  • Figure 3: Visual comparison of our method output (before the time-series analysis block), with respect to input data (S1 & S2) and reference data. Each row represents, $1)$ S1 data, $2)$ S2 data, $3)$ method results, 4) ground truth.
  • Figure 4: Investigation on the temporal trends in the water volume variation.
  • Figure 5: Olivo Dam in different seasons: (a) spring, April 13, 2016; (b) summer, August 21, 2016; (c) autumn, October 10, 2016.