A carregar...
Projeto de investigação
Sem título
Financiador
Autores
Publicações
Spatially explicit assessment of carbon storage and sequestration in forest ecosystems
Publication . Almeida, Bruna; Monteiro, Luís; Tiengo, Rafaela; Gil, Artur; Cabral, Pedro; Information Management Research Center (MagIC) - NOVA Information Management School; NOVA Information Management School (NOVA IMS); Elsevier Science Publisher B.V.
Forests play an important role in the global carbon cycle, making accurate assessments of carbon dynamics essential for effective forest management and climate change mitigation strategies. This research examines the spatiotemporal patterns of carbon storage and sequestration (CSS) in forests' aboveground biomass using satellite data, machine learning (Support Vector Machines), carbon modeling and spatial statistics. The methodology follows a two-step classification process: (i) binary forest classification and (ii) forest type classification, mapping seven forest types within two main categories - Broadleaves (Quercus suber, Quercus ilex, Eucalyptus sp., and other species) and Coniferous (Pinus pinaster, Pinus pinea, and other species). We analyzed the relationship between forest type and CSS at the Nomenclature of Territorial Units for Statistics (NUTS) III level and identified spatial clusters, outliers, and hot and cold spots of carbon sequestration at the municipal level across mainland Portugal. The broadleaved category demonstrated the highest classification accuracy in both years, decreasing slightly from 90.3% in 2018 to 89% in 2022, while the Coniferous group had the lowest accuracy, declining from 84.1% in 2018 to 83.6% in 2022. Anselin's Local Moran's I identified clusters of carbon sequestration, while the Getis-Ord Gi analysis confirmed these findings, revealing statistically significant hotspots of carbon sequestration in the northern and central regions and cold spots in the southern region. By providing insights at the sub-regional and municipal levels, this study offers a robust framework to support sustainable forest management and climate change mitigation strategies. Moreover, it can assist decision-makers in prioritizing natural capital, and developing nature-based solutions to tackle climate change and biodiversity loss.
Data-Driven Modelling of Freshwater Ecosystems
Publication . Almeida, Bruna; Cabral, Pedro; Information Management Research Center (MagIC) - NOVA Information Management School; NOVA Information Management School (NOVA IMS)
Freshwater ecosystems are primarily impacted by climate, land use and land cover changes, and over-abstraction. Satellite Earth observation (SEO) data and technologies are key in environmental modelling and support decisions. These technologies combined with machine learning (ML) are a powerful approach for modelling freshwater ecosystems at a multiscale level. The goal of this study is to present a set of reference data and guidelines that can be used to estimate the water and wetness probability index (WWPI) in different spatial and temporal scales. To find the best model’s predictors, sensitivity analyses were carried out in a predictive ML model implemented in a transnational river basin district (Portugal – Spain), the Tagus Basin. Satellite imagery, satellite-derived data, biophysical variables, and landscape characteristics were the explanatory variables evaluated in the sensitivity analyses, and some of them were included in the framework as a reference source of spatial data.
Satellite-based Machine Learning modelling of Ecosystem Services indicators
Publication . Almeida, Bruna; David, João; Campos, Felipe Siqueira e; Cabral, Pedro; Information Management Research Center (MagIC) - NOVA Information Management School; NOVA Information Management School (NOVA IMS); Elsevier Science B.V., Amsterdam.
Satellite-based Machine Learning (ML) modelling has emerged as a powerful tool to understand and quantify spatial relationships between landscape dynamics, biophysical variables and natural stocks. Ecosystem Services indicators (ESi) provide qualitative and quantitative information aiding the assessment of ecosystems’ status. Through a systematic meta-analysis following the PRISMA guidelines, studies from one decade (2012–2022) were analyzed and synthesized. The results indicated that Random Forest emerged as the most frequently utilized ML algorithm, while Landsat missions stood out as the primary source of Satellite Earth Observation (SEO) data. Nonetheless, authors favoured Sentinel-2 due to its superior spatial, spectral, and temporal resolution. While 30% of the examined studies focused on modelling proxies of climate regulation services, assessments of natural stocks such as biomass, water, food production, and raw materials were also frequently applied. Meta-analysis illustrated the utilization of classification and regression tasks in estimating measurements of ecosystems' extent and conditions and findings underscored the connections between established methods and their replication. This study offers current perspectives on existing satellite-based approaches, contributing to the ongoing efforts to employ ML and artificial intelligence for unveiling the potential of SEO data and technologies in modelling ESi.
A hybrid modelling approach for detecting seasonal variations in inland green-blue ecosystems
Publication . Almeida, Bruna; Cabral, Pedro; Information Management Research Center (MagIC) - NOVA Information Management School; NOVA Information Management School (NOVA IMS); Elsevier Science Publisher B.V.
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.
A Hybrid Modelling Approach for Detecting Seasonal Variations in Inland Green-Blue Ecosystems [poster]
Publication . Almeida, Bruna; Cabral, Pedro; Information Management Research Center (MagIC) - NOVA Information Management School
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. In the context of climate change, Portugal is recognized as a hotspot among the most vulnerable European countries. Recent studies have shown evidence of climatic changes, such as the long periods of drought recorded in 1990, 2004/2005 and2012. The more frequent occurrence of these events is increasing the severity of seasonality effects on GBE and compromising the provision of services such as freshwater supply, and consequently crop and wood production, and carbon storage and sequestration.
Unidades organizacionais
Descrição
Palavras-chave
Contribuidores
Financiadores
Entidade financiadora
Fundação para a Ciência e a Tecnologia
Programa de financiamento
3599-PPCDT
Número da atribuição
EXPL/CTA-AMB/0165/2021