From fractions to fragments : Policy to practice through AI-driven multiscale spatial planning for groundwater nitrate management
Naghibi, Amir LU ; Ahmadi, Kourosh LU ; Mousavi, Seyed Mohsen LU ; Haghighi, Ali Torabi ; Nilsson, Bertel and Berndtsson, Ronny LU
(2026)
In Water Research
296.
p.125597-125597
- Abstract
Diffuse nitrate pollution remains a persistent threat to drinking-water resources, yet current predictive frameworks rarely capture how the spatial composition (land-cover fractions) and configuration (landscape fragmentation) of land systems jointly modulate leaching. This study presents a novel multiscale framework integrating hydro-climatic, soil and anthropogenic predictors with land-cover fractions and seven fragmentation metrics calculated at nested grids of 50, 100, 200, and 500 m. This AI-based framework implemented feature selection techniques to identify the top 30 input features (out of 116 initial factors) and then modelled nitrate vulnerability in two settings: i) only using hydroclimatic, anthropogenic and soil factors;... (More)
Diffuse nitrate pollution remains a persistent threat to drinking-water resources, yet current predictive frameworks rarely capture how the spatial composition (land-cover fractions) and configuration (landscape fragmentation) of land systems jointly modulate leaching. This study presents a novel multiscale framework integrating hydro-climatic, soil and anthropogenic predictors with land-cover fractions and seven fragmentation metrics calculated at nested grids of 50, 100, 200, and 500 m. This AI-based framework implemented feature selection techniques to identify the top 30 input features (out of 116 initial factors) and then modelled nitrate vulnerability in two settings: i) only using hydroclimatic, anthropogenic and soil factors; ii) the same factors plus land-cover fractions, and landscape fragmentation. The classification was made in an ordinal manner using a multi-layer perceptron encoder (MLP-encoder) benchmarked with proportional-odds ordinal regression with 100 repetitions on different data split configurations. When including the introduced land-cover fractions and landscape fragmentation at multiscale, the accuracy of the model significantly improved by 11%. The results confirm that incorporating both land-use composition and fragmentation at an intermediate scale markedly enhances nitrate-vulnerability mapping and provides spatially explicit, policy-relevant levers for intervention design. These levers include limiting large contiguous cropland blocks and conserving forest-wetland complexes to support catchment management and groundwater-protection planning at municipal and governmental levels.
(Less)
- author
- Naghibi, Amir
LU
; Ahmadi, Kourosh
LU
; Mousavi, Seyed Mohsen
LU
; Haghighi, Ali Torabi
; Nilsson, Bertel
and Berndtsson, Ronny
LU
- organization
- publishing date
- 2026-02-18
- type
- Contribution to journal
- publication status
- epub
- subject
- in
- Water Research
- volume
- 296
- pages
- 125597 - 125597
- publisher
- Elsevier
- external identifiers
-
- pmid:41747611
- scopus:105030926529
- ISSN
- 1879-2448
- DOI
- 10.1016/j.watres.2026.125597
- project
- The United Nations University Hub: Water in a Changing Environment (WICE)
- language
- English
- LU publication?
- yes
- additional info
- Copyright © 2026. Published by Elsevier Ltd.
- id
- 9f684f0d-eede-4bdc-9563-eb35409734ff
- date added to LUP
- 2026-03-02 15:53:33
- date last changed
- 2026-04-14 12:06:05
@article{9f684f0d-eede-4bdc-9563-eb35409734ff,
abstract = {{<p>Diffuse nitrate pollution remains a persistent threat to drinking-water resources, yet current predictive frameworks rarely capture how the spatial composition (land-cover fractions) and configuration (landscape fragmentation) of land systems jointly modulate leaching. This study presents a novel multiscale framework integrating hydro-climatic, soil and anthropogenic predictors with land-cover fractions and seven fragmentation metrics calculated at nested grids of 50, 100, 200, and 500 m. This AI-based framework implemented feature selection techniques to identify the top 30 input features (out of 116 initial factors) and then modelled nitrate vulnerability in two settings: i) only using hydroclimatic, anthropogenic and soil factors; ii) the same factors plus land-cover fractions, and landscape fragmentation. The classification was made in an ordinal manner using a multi-layer perceptron encoder (MLP-encoder) benchmarked with proportional-odds ordinal regression with 100 repetitions on different data split configurations. When including the introduced land-cover fractions and landscape fragmentation at multiscale, the accuracy of the model significantly improved by 11%. The results confirm that incorporating both land-use composition and fragmentation at an intermediate scale markedly enhances nitrate-vulnerability mapping and provides spatially explicit, policy-relevant levers for intervention design. These levers include limiting large contiguous cropland blocks and conserving forest-wetland complexes to support catchment management and groundwater-protection planning at municipal and governmental levels.</p>}},
author = {{Naghibi, Amir and Ahmadi, Kourosh and Mousavi, Seyed Mohsen and Haghighi, Ali Torabi and Nilsson, Bertel and Berndtsson, Ronny}},
issn = {{1879-2448}},
language = {{eng}},
month = {{02}},
pages = {{125597--125597}},
publisher = {{Elsevier}},
series = {{Water Research}},
title = {{From fractions to fragments : Policy to practice through AI-driven multiscale spatial planning for groundwater nitrate management}},
url = {{http://dx.doi.org/10.1016/j.watres.2026.125597}},
doi = {{10.1016/j.watres.2026.125597}},
volume = {{296}},
year = {{2026}},
}