TY - JOUR
T1 - A hybrid modelling approach for detecting seasonal variations in inland green-blue ecosystems
AU - Almeida, Bruna
AU - Cabral, Pedro
N1 - info:eu-repo/grantAgreement/FCT/3599-PPCDT/EXPL%2FCTA-AMB%2F0165%2F2021/PT#
info:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDB%2F04152%2F2020/PT#
Almeida, B., & Cabral, P. (2023). A hybrid modelling approach for detecting seasonal variations in inland green-blue ecosystems. Remote Sensing Applications: Society and Environment, 33(January 2024), [101121]. https://doi.org/10.1016/j.rsase.2023.101121 --- This study was supported by the research project MaSOT – Mapping Ecosystem Services from Earth Observations, funded by the Portuguese Science Foundation – FCT [EXPL/CTA-AMB/0165/2021]. The authors gratefully acknowledge the financial support of the FCT, through the MagIC Research (Centro de Investigação em Gestão de Informação - UIDB/04152/2020). We are grateful for the constructive remarks from two anonymous reviewers.
PY - 2024/1
Y1 - 2024/1
N2 - Deforestation, environmental pollution, and the overexploitation of resources, in addition to the Earth's natural cycles, are scaling up the impacts of climate change in the provision of Ecosystem Services (ES). Green-Blue Ecosystems (GBE) are impacted by climatic conditions, topography, and water presence. Data-driven modelling techniques may effectively capture the effects of seasonal variations while modelling natural ecosystems. This research proposes a hybrid modelling approach that combines Deep Learning and traditional Machine Learning, Sensitivity Analysis and Feature Importance Evaluation (FIE) to investigate seasonality effects on mapping GBE. The models, built using satellite imagery from the Spring and Summer seasons of the Mediterranean climate zone, included spectral indices, topography (DEM), and groundwater depth (GD). The model that best suited the analysis was selected using sensitivity tests and hyperparameter optimization. The study shows that land cover classes of transitional woodland shrubs, inland marshes, cultivated land parcels, and watercourses are better classified in the Spring, with an accuracy of 0.814. FIE indicates that spectral indices are the most important predictors for detecting green ecosystems in both seasons. Additionally, DEM and GD are the most relevant predictors to classify watercourses in the Summer. An analytical examination of the input data and hyperparameter settings facilitates understanding of models' behaviour while improving models' prediction. This research provides an advanced understanding of the effects of seasonal variations on the status of GBE and enhances understanding of modelling ES in areas with a growing need for changes in land use and high water supply demand.
AB - Deforestation, environmental pollution, and the overexploitation of resources, in addition to the Earth's natural cycles, are scaling up the impacts of climate change in the provision of Ecosystem Services (ES). Green-Blue Ecosystems (GBE) are impacted by climatic conditions, topography, and water presence. Data-driven modelling techniques may effectively capture the effects of seasonal variations while modelling natural ecosystems. This research proposes a hybrid modelling approach that combines Deep Learning and traditional Machine Learning, Sensitivity Analysis and Feature Importance Evaluation (FIE) to investigate seasonality effects on mapping GBE. The models, built using satellite imagery from the Spring and Summer seasons of the Mediterranean climate zone, included spectral indices, topography (DEM), and groundwater depth (GD). The model that best suited the analysis was selected using sensitivity tests and hyperparameter optimization. The study shows that land cover classes of transitional woodland shrubs, inland marshes, cultivated land parcels, and watercourses are better classified in the Spring, with an accuracy of 0.814. FIE indicates that spectral indices are the most important predictors for detecting green ecosystems in both seasons. Additionally, DEM and GD are the most relevant predictors to classify watercourses in the Summer. An analytical examination of the input data and hyperparameter settings facilitates understanding of models' behaviour while improving models' prediction. This research provides an advanced understanding of the effects of seasonal variations on the status of GBE and enhances understanding of modelling ES in areas with a growing need for changes in land use and high water supply demand.
KW - Remote sensing
KW - Machine learning
KW - Land use classification
KW - Aquatic ecosystems
KW - Terrestrial ecosystems
KW - Spatiotemporal analysis
UR - http://www.scopus.com/inward/record.url?scp=85179820488&partnerID=8YFLogxK
UR - https://www.webofscience.com/wos/woscc/full-record/WOS:001136924500001
U2 - 10.1016/j.rsase.2023.101121
DO - 10.1016/j.rsase.2023.101121
M3 - Article
SN - 2352-9385
VL - 33
SP - 1
EP - 15
JO - Remote Sensing Applications: Society and Environment
JF - Remote Sensing Applications: Society and Environment
M1 - 101121
ER -