Continuous Satellite Monitoring of Reservoir Capacity Loss Using Deep Learning and Stochastic Mapping: The Poechos Reservoir and Regional Transferability in Northern Peru

Breña Aliaga J.C.; Bourrel L.; Cruz Machacuay J.; Breña Ore J.L.; Felipe O.; Rau P.; Lavado-Casimiro W. · Remote Sensing (2026) · DOI: 10.3390/rs18172901

Resumen

Sedimentation is eroding the water security of reservoirs in hydrologically active basins: the Poechos reservoir (Peru) has lost 62% of its original 887.7 hm3 capacity in 48 years, yet its Elevation–Area–Volume (EAV) curve is refreshed only by bathymetric surveys at decade-plus intervals, compromising flood regulation and the water supply for over 100,000 ha of farmland. To close this gap, we propose an integrated, low-cost, fully reproducible framework that reconstructs the EAV curve from freely available satellite data: Sentinel-1 SAR (287 acquisitions, 2021–2026), PlanetScope imagery as ground truth (23 dates), and Surface Water and Ocean Topography (SWOT) altimetry (53 validated passes, 2023–2026). Water surfaces were delineated with a deep learning segmentation model (Feature Pyramid Network with an InceptionV4 encoder), selected among nine architecture–encoder combinations and calibrated to a 0.64 decision threshold, achieving a 90.66% Intersection over Union (IoU) and a 95.10% F1 score; a stochastic quantile mapping algorithm then asynchronously coupled the area and elevation series. The resulting EAV curve matched daily operational records from Peru’s National Water Authority (ANA) with high precision (NSE = 0.94, R2 = 0.96, and RMSE = 25.93 hm3); the residual bias (BIAS = −11.23 hm3) reflects active sedimentation unaccounted for in the official curve. This bias peaked at an accumulated deficit of 24.5 hm3 during the 2023–2024 hydrological year (3.5 hm3/year), of which up to 19.6 hm3 is attributed to the 2023 Yaku cyclone as a phenomenologically scaled upper-bound estimate (9.8–19.6 hm3 across 40–80% attribution fractions), since SWOT was not yet operational during the event. Updating every 21 days under any weather and requiring no new field campaigns beyond the baseline bathymetric anchor, the trained ensemble was further transferred zero-shot to three additional reservoirs (San Lorenzo, Tinajones, and Gallito Ciego), demonstrating a scalable path from infrequent static assessments to near-continuous, dynamic monitoring of water storage.

Instituciones: Universidad Nacional de Ingeniería; Universidad de Ingeniería y Tecnología