Skip to content
DraconiticResearch
Search Sources API
226,742 studies31 sourcesUpdated 52 min ago
PreprintCC BY 4.0EarthArXiv

Irrigation-driven land subsidence on the Barind Tract, northwest Bangladesh: two-track Sentinel-1 InSAR, GNSS-tied time series and spatially cross-validated explainable machine learning

Abstract

The Barind Tract of northwest Bangladesh is the country’s most intensively groundwater-irrigated region, yet its ground motion has been measured only at isolated points. We processedascendinganddescendingSentinel-1small-baseline InSAR networks for 2017–2025, referenced them to a continuous GNSS station and converted line-of-sight rates to vertical velocity. In the ascending track, co herent land subsides at a median of −10.1 mmyr−1 (median formal uncertainty 0.58 mm yr−1, plus a common ±1.7 mmyr−1 GNSS-tie uncertainty), and 51% of it subsides faster than 10 mm yr−1. Rates reach −11.2 ± 1.2 mmyr−1 at Godagari on the Barind margin, against −1.8 ± 1.1 mmyr−1 on the active Ganges flood plain; 1-km block medians from the two tracks correlate at 𝑟 = 0.56. GLDAS-2.2 groundwater storage declined by 7.2±1.2 mmyr−1, and the fitted seasonal ground low lags the April storage minimum by three to four months, consistent with de layed aquitard drainage. An ERA5 tropospheric correction changed velocities by a median of 0.03 mm yr−1 and shifted this timing by at most three weeks at three of four sites. Randomforest andXGBoostmodelsexplain37–47%ofthespatialvariance under 5-km spatial block cross-validation; random cross-validation inflates 𝑅2 by 0.09–0.13, and omitting ramp removal raises it to 0.69. SHAP effects with the same direction in both tracks identify elevation, built-up density and local Boro irrigation intensity as robust controls. Subsidence removes at least 25 million m3 of ground volume per year, of the same order as the groundwater-storage decline, and601km ofmainroadsand101km of railway lieongroundsubsidingfasterthan 10 mm yr−1. Spatial cross-validation and cross-track consistency should precede physical interpretation of machine-learning attributions of subsidence.

Related

  1. Depth-dependent soil water-salt relationships in the Hetao Irrigation District, arid Northwest China: Implications for sustainable management
    Yuanqing Cao, Huihui Wang, Xuan Chen +1
    PLOS OnePeer-reviewedCC BYFull textEnvironmental chemistryHydrology & soilsPLOSEurope PMC
  2. Integrating Sentinel-1 Radar Soil Moisture and Explainable Machine Learning to Quantify Irrigation-Induced Groundwater Fluxes in the Hajdúság Region, Eastern Hungary
    Gift Siphiwe Nxumalo, Tondani Sanah Ramabulana, Dávid Pásztor +1
    EGUspherePreprintCC BY 4.0General earth scienceEGUsphere
  3. Explainable spatiotemporal Graph Neural Networks: Multi-City PM2.5 forecasting in Bangladesh with geographic graph topology validation
    Pritom Ray Nobin
    PLOS OnePeer-reviewedCC BY 4.0Full textEnvironmental chemistryAtmospheric science & meteorologyPLOS
  4. Sea level rise and subsidence compound flood risks on the century-old Treasure Island
    Guoqiang Shi, Roland Bürgmann, Alessandro Ferretti +3
    Communications Earth & EnvironmentPeer-reviewedCC BY 4.0General earth scienceNatureCrossref
  5. Human-induced subsidence exceeds sea-level rise in driving future coastal flood exposure in China’s Greater Bay Area
    Xudong Wang, Mi Jiang, Leonard O. Ohenhen +6
    Communications Earth & EnvironmentPeer-reviewedCC BYFull textClimate scienceDOAJ
BibTeX
@misc{zaman2026irrigationdriven,
  title = {{Irrigation-driven land subsidence on the Barind Tract, northwest Bangladesh: two-track Sentinel-1 InSAR, GNSS-tied time series and spatially cross-validated explainable machine learning}},
  author = {Farheen Zaman and Ashfaq Raveed},
  howpublished = {EarthArXiv},
  year = {2026},
  month = nov,
  doi = {10.31223/x50z4k},
  url = {https://eartharxiv.org/repository/view/16080/},
  note = {CC BY 4.0},
}
RIS
TY  - UNPB
TI  - Irrigation-driven land subsidence on the Barind Tract, northwest Bangladesh: two-track Sentinel-1 InSAR, GNSS-tied time series and spatially cross-validated explainable machine learning
AU  - Farheen Zaman
AU  - Ashfaq Raveed
PY  - 2026
DA  - 2026/11/12
PB  - EarthArXiv
DO  - 10.31223/x50z4k
UR  - https://eartharxiv.org/repository/view/16080/
AB  - The Barind Tract of northwest Bangladesh is the country’s most intensively groundwater-irrigated region, yet its ground motion has been measured only at isolated points. We processedascendinganddescendingSentinel-1small-baseline InSAR networks for 2017–2025, referenced them to a continuous GNSS station and converted line-of-sight rates to vertical velocity. In the ascending track, co herent land subsides at a median of −10.1 mmyr−1 (median formal uncertainty 0.58 mm yr−1, plus a common ±1.7 mmyr−1 GNSS-tie uncertainty), and 51% of it subsides faster than 10 mm yr−1. Rates reach −11.2 ± 1.2 mmyr−1 at Godagari on the Barind margin, against −1.8 ± 1.1 mmyr−1 on the active Ganges flood plain; 1-km block medians from the two tracks correlate at 𝑟 = 0.56. GLDAS-2.2 groundwater storage declined by 7.2±1.2 mmyr−1, and the fitted seasonal ground low lags the April storage minimum by three to four months, consistent with de layed aquitard drainage. An ERA5 tropospheric correction changed velocities by a median of 0.03 mm yr−1 and shifted this timing by at most three weeks at three of four sites. Randomforest andXGBoostmodelsexplain37–47%ofthespatialvariance under 5-km spatial block cross-validation; random cross-validation inflates 𝑅2 by 0.09–0.13, and omitting ramp removal raises it to 0.69. SHAP effects with the same direction in both tracks identify elevation, built-up density and local Boro irrigation intensity as robust controls. Subsidence removes at least 25 million m3 of ground volume per year, of the same order as the groundwater-storage decline, and601km ofmainroadsand101km of railway lieongroundsubsidingfasterthan 10 mm yr−1. Spatial cross-validation and cross-track consistency should precede physical interpretation of machine-learning attributions of subsidence.
ER  -