Deep Learning and Transformer Models for Groundwater Level Prediction in the Marvdasht Plain: Protecting UNESCO Heritage Sites—Persepolis and Naqsh-e Rustam

Deep Learning and Transformer Models for Groundwater Level Prediction in the Marvdasht Plain: Protecting UNESCO Heritage Sites—Persepolis and Naqsh-e Rustam

Groundwater level monitoring is crucial for assessing hydrological responses to climate change and human activities, which pose significant threats to the sustainability of semi-arid aquifers and the cultural heritage they sustain. This study presents an integrated remote sensing and transformer-bas...

Full description

Saved in:
Bibliographic Details
Main Authors: Peyman Heidarian, Franz Pablo Antezana Lopez, Yumin Tan, Somayeh Fathtabar Firozjaee, Tahmouras Yousefi, Habib Salehi, Ava Osman Pour, Maria Elena Oscori Marca, Guanhua Zhou, Ali Azhdari, Reza Shahbazi
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Remote Sensing
Subjects:
transformer models
neural networks
InSAR
deep learning
land subsidence
water resource management
Online Access:https://www.mdpi.com/2072-4292/17/14/2532
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Groundwater level monitoring is crucial for assessing hydrological responses to climate change and human activities, which pose significant threats to the sustainability of semi-arid aquifers and the cultural heritage they sustain. This study presents an integrated remote sensing and transformer-based deep learning framework that combines diverse geospatial datasets to predict spatiotemporal variations across the plain near the Persepolis and Naqsh-e Rustam archaeological complexes—UNESCO World Heritage Sites situated at the plain’s edge. We assemble 432 synthetic aperture radar (SAR) scenes (2015–2022) and derive vertical ground motion rates greater than −180 mm yr<sup>−1</sup>, which are co-localized with multisource geoinformation, including hydrometeorological indices, biophysical parameters, and terrain attributes, to train transformer models with traditional deep learning methods. A sparse probabilistic transformer (ConvTransformer) trained on 95 gridded variables achieves an out-of-sample R<sup>2</sup> = 0.83 and RMSE = 6.15 m, outperforming bidirectional deep learning models by >40%. Scenario analysis indicates that, in the absence of intervention, subsidence may exceed 200 mm per year within a decade, threatening irreplaceable Achaemenid stone reliefs. Our results indicate that attention-based networks, when coupled to synergistic geodetic constraints, enable early-warning quantification of groundwater stress over heritage sites and provide a scalable template for sustainable aquifer governance worldwide.
ISSN:2072-4292

Similar Items