Cleaner peri-urban agricultural transitions under nitrogen-related water constraints: A teacher-validated evaluation of land-use alternatives in Almere Oosterwold, the Netherlands

Peri-urban agriculture is increasingly expected to contribute to sustainable urban development while reducing the environmental pressures associated with land-use change and water-quality degradation. A key challenge is how to compare alternative agricultural configurations that maintain productive land use while lowering nitrogen-related environmental burdens before implementation. This study develops a teacher-validated framework for evaluating cleaner peri-urban agricultural land-use alternatives, using Almere Oosterwold, the Netherlands, as a living-lab case. We combine the InVEST Nutrient Delivery Ratio (NDR) model as a process-based teacher model with deep surrogate models and the Non-dominated Sorting Genetic Algorithm II (NSGA-II) to generate and screen alternative crop-pattern configurations under explicit feasibility constraints. Candidate Pareto solutions are then materialised and re-evaluated with the teacher model, which separates rapid screening from final environmental interpretation. The framework is designed around an explicit scale mismatch: land-use decisions are taken on individual parcels and governance blocks, whereas nitrogen impacts accumulate over the whole planning domain. Under the available data regime, the governance-aligned graph surrogate outperforms pixel-level emulation and provides acceptable screening fidelity on the 32 × 32 intervention grid. Teacher validation shows that the best alternatives lower domain-integrated subsurface nitrogen export by up to 998.55 kg N yr −1 (ΔN = −998.55 kg N yr −1 ), equivalent to about 10.8% of the baseline, at an intervention footprint of about 2392 ha. Screening reliability is further quantified through rank association, top- K precision and Pareto overlap. The contribution of the study is to link cleaner peri-urban agricultural transition, nitrogen-related environmental management and land-use alternative appraisal in a single reproducible framework for comparing productive configurations under water-quality constraints. More broadly, the study shows how rapid alternative exploration and teacher-validated environmental evidence can be combined to support cleaner and more sustainable peri-urban land-use transitions.

Authors

Institutions

Publication Details

Journal
Journal of Cleaner Production
Published
2026-09-30
DOI
https://doi.org/10.1016/j.jclepro.2026.149588
Primary Topic
Urban Agriculture and Sustainability
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
article

Cleaner peri-urban agricultural transitions under nitrogen-related water constraints: A teacher-validated evaluation of land-use alternatives in Almere Oosterwold, the Netherlands

Steffen Nijhuis, Yu Huan, Nico Tillie
Journal of Cleaner Production
Urban Agriculture and Sustainability
article

Cleaner peri-urban agricultural transitions under nitrogen-related water constraints: A teacher-validated evaluation of land-use alternatives in Almere Oosterwold, the Netherlands

Steffen Nijhuis, Yu Huan, Nico Tillie
article en

Abstract

Peri-urban agriculture is increasingly expected to contribute to sustainable urban development while reducing the environmental pressures associated with land-use change and water-quality degradation. A key challenge is how to compare alternative agricultural configurations that maintain productive land use while lowering nitrogen-related environmental burdens before implementation. This study develops a teacher-validated framework for evaluating cleaner peri-urban agricultural land-use alternatives, using Almere Oosterwold, the Netherlands, as a living-lab case. We combine the InVEST Nutrient Delivery Ratio (NDR) model as a process-based teacher model with deep surrogate models and the Non-dominated Sorting Genetic Algorithm II (NSGA-II) to generate and screen alternative crop-pattern configurations under explicit feasibility constraints. Candidate Pareto solutions are then materialised and re-evaluated with the teacher model, which separates rapid screening from final environmental interpretation. The framework is designed around an explicit scale mismatch: land-use decisions are taken on individual parcels and governance blocks, whereas nitrogen impacts accumulate over the whole planning domain. Under the available data regime, the governance-aligned graph surrogate outperforms pixel-level emulation and provides acceptable screening fidelity on the 32 × 32 intervention grid. Teacher validation shows that the best alternatives lower domain-integrated subsurface nitrogen export by up to 998.55 kg N yr −1 (ΔN = −998.55 kg N yr −1 ), equivalent to about 10.8% of the baseline, at an intervention footprint of about 2392 ha. Screening reliability is further quantified through rank association, top- K precision and Pareto overlap. The contribution of the study is to link cleaner peri-urban agricultural transition, nitrogen-related environmental management and land-use alternative appraisal in a single reproducible framework for comparing productive configurations under water-quality constraints. More broadly, the study shows how rapid alternative exploration and teacher-validated environmental evidence can be combined to support cleaner and more sustainable peri-urban land-use transitions.

Journal of Cleaner ProductionVol. 579
Delft University of Technology (NL)
Zero hunger
Openalex Percentile: Top 14%
Urban Agriculture and Sustainability
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.