Combining machine learning and spatial data processing techniques for allocation of large-scale nature-based solutions - research focus

Aug 4, 2026

Climate change increases hydro-meteorological hazards, making hydro-meteorological risk management and planning more urgent. Nature-based solutions (NBSs) integrate hydrology, geomorphology, hydraulic, and ecological dynamics, yet spatial allocation methods for large-scale NBSs remain limited. The study develops new toolboxes and extends an existing methodology by implementing GIS-based spatial analysis, combining machine learning and spatial data processing with hydrodynamic modelling. Case studies in the Netherlands, Serbia, and Bolivia evaluate rainwater harvesting, wetland restoration, and natural riverbank stabilisation, using available project and regional datasets.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages14

Reading Time35 min

AccessFree to download

Introduction

Nature-based solutions and hazard context

Need for large-scale spatial allocation

Methodology overview

GIS-based multi-criteria allocation

Machine learning and spatial data processing

Integration with 2D hydrodynamic modelling

Case studies

Netherlands: rainwater harvesting

Serbia: wetland restoration

Bolivia: natural riverbank stabilisation

Findings and implications

© 2023 The Authors Blue-Green Systems Vol 5 No 2, 186 doi: 10.2166/bgs.2023.040 Combining machine learning and spatial data processing techniques for allocation of large-scale nature-based solutions Beatriz Emma Gutierrez Caloir a, Yared Abayneh Abebe b, c, Zoran Vojinovic b, d, e, Arlex Sanchez b, Adam Mubeen b, f, Laddaporn Ruangpan b, f, *, Natasa Manojlovic g, Jasna Plavsic d and Slobodan Djordjevic e a Water Science and Engineering – Hydroinformatics Department, IHE Delft Institute for Water Education, Delft, The Netherlands b Water Supply, Sanitation and Environmental Engineering Department, IHE Delft Institute for Water Education, Delft, The Netherlands c Department of Hydraulic Engineering, Faculty of Civil Engineering and Geosciences, Delft University of Technology, Delft, The Netherlands d Faculty of Civil Engineering, University of Belgrade, Belgrade, Serbia e College of Engineering, Mathematics and Physics, University of Exeter, Exeter EX4 4QF, UK f Faculty of Applied Science, Delft University of Technology, Delft, The Netherlands g Institute of River & Coastal Engineering, Hamburg University of Technology, Hamburg, Germany *Corresponding author. E-mail: [l.ruangpan@un-ihe.org](l.ruangpan@un-ihe.org) BEGC, 0000-0002-5663-5377; YAA, 0000-0002-6416-6443; ZV, 0000-0002-7601-4041; AS, 0000-0003-3146-2841; AM, 0000-0003-1934-6813; LR, 0000-0002-7803-0600; NM, 0000-0002-0958-655X; JP, 0000-0001-9679-8851; SD, 0000-0003-1682-1383 ABSTRACT The escalating impacts of climate change trigger the necessity to deal with hydro-meteorological hazards. Nature-based solutions (NBSs) seem to be a suitable response, integrating the hydrology, geomorphology, hydraulic, and ecological dynamics. While there are some methods and tools for suitability mapping of small-scale NBSs, literature concerning the spatial allocation of large-scale NBSs is still lacking. The present work aims to develop new toolboxes and enhance an existing methodology by developing spatial analysis tools within a geographic information system (GIS) environment to allocate large-scale NBSs based on a multi-criteria algorithm. The methodologies combine machine learning spatial data processing techniques and hydrodynamic modelling for allocation of large-scale NBSs. The case studies concern selected areas in the Netherlands, Serbia, and Bolivia, focusing on three large-scale NBS: rainwater harvesting, wetland restoration, and natural riverbank stabilisation. Information available from the EC H2020 RECONECT project as well as other available data for the speciﬁc study areas was used. The research highlights the signiﬁcance of incorporating machine learning, GIS, and remote sensing techniques for the suitable allocation of large-scale NBSs. The ﬁndings may offer new insights for decision-makers and other stakeholders involved in future sustainable environmental planning and climate change adaptation. Key words: ﬂood risk reduction, large-scale nature-based solutions, machine learning, NBS planning, spatial data processing HIGHLIGHTS • The paper provides enhanced methodologies for mapping NBSs using novel techniques. • The methodology combines machine learning (ML) and spatial data processing techniques for allocation of large-scale NBSs. • The methodology also includes outputs from a 2D hydrodynamic model. • The methodologies have been thought to be applicable worldwide and not only in the study areas, and it is only necessary to have available data. 1. INTRODUCTION Hydro-meteorological hazards such as ﬂoods, landslides, droughts, and heatwaves have increased globally due to human activities and climate change (Singh et al. 2016) . These hazards produce environmental damage, life losses, and world economy stress every year (IPCC 2014) . To reduce impacts of climate change, nature-based solutions (NBSs) are suitable measures, especially considering the conventional hydraulic structures are not sustainable and adaptive. NBSs are so

FAQs

Why are large-scale nature-based solutions difficult to allocate spatially?

Although suitability mapping exists for small-scale NBSs, the literature lacks approaches for the spatial allocation of large-scale NBSs, where effectiveness depends on broader interactions with catchment processes.

What does the proposed method combine to allocate large-scale NBSs?

The methodology integrates GIS-based spatial analysis using a multi-criteria algorithm, machine learning spatial data processing techniques, and outputs from a 2D hydrodynamic model.

Which NBS types are tested in the case studies and where?

The study focuses on rainwater harvesting, wetland restoration, and natural riverbank stabilisation, using selected areas in the Netherlands, Serbia, and Bolivia.

Aug 4, 2026

Upload by Evangeline