Indicator-based assessment of post-fire recovery dynamics using satellite NDVI time-series

Torres, João; Gonçalves, João; Marcos, Bruno; João, Honrado

doi:10.1016/j.ecolind.2018.02.008

Cited by 54 publications

(26 citation statements)

References 71 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The study of post-fire regeneration is an important aspect of understanding forest and ecosystem responses and resilience to wildfire disturbances, with important ecological and economic consequences. RF, for example, has been a popular ML method for understanding the important variables driving post-fire regeneration (João et al 2018;Vijayakumar et al 2016). Burn severity is an important metric for understanding the impacts of wildfire on vegetation and post-fire regeneration, soils, and potential successional shifts in forest composition and, as such, has been included in many ML studies in this section, including Barrett et al 2011 2012, and Thompson and Spies (2010).…”

Section: Post-fire Regeneration Succession and Ecologymentioning

confidence: 99%

A review of machine learning applications in wildfire science and management

et al. 2020

View full text Add to dashboard Cite

Artiﬁcial intelligence has been applied in wildﬁre science and management since the 1990s, with early applications including neural networks and expert systems. Since then the ﬁeld has rapidly progressed congruently with the wide adoption of machine learning (ML) methods in the environmental sciences. Here, we present a scoping review of ML applications in wildﬁre science and management. Our overall objective is to improve awareness of ML methods among wildﬁre researchers and managers, as well as illustrate the diverse and challenging range of problems in wildﬁre science available to ML data scientists. To that end, we ﬁrst present an overview of popular ML approaches used in wildﬁre science to date, and then review the use of ML in wildﬁre science as broadly categorized into six problem domains, including: 1) fuels characterization, ﬁre detection, and mapping; 2) ﬁre weather and climate change; 3) ﬁre occurrence, susceptibility, and risk; 4) ﬁre behavior prediction; 5) ﬁre eﬀects; and 6) ﬁre management. Furthermore, we discuss the advantages and limitations of various ML approaches relating to data size, computational requirements, generalizability, and interpretability, as well as identify opportunities for future advances in the science and management of wildﬁres within a data science context. In total, we identfied 300 relevant publications up to the end of 2019, where the most frequently used ML methods across problem domains included random forests, MaxEnt, artiﬁcial neural networks, decision trees, support vector machines, and genetic algorithms. As such, there exists opportunities to apply more current ML methods — including deep learning and agent based learning — in the wildﬁre sciences, especially in instances involving very large multivariate datasets. We must recognize, however, that despite the ability of ML methods to learn on their own, expertise in wildﬁre science is necessary to ensure realistic modelling of ﬁre processes across multiple scales, while the complexity of some ML methods, such as deep learning, requires a dedicated and sophisticated knowledge of their application. Finally, we stress that the wildﬁre research and management communities play an active role in providing relevant, high quality, and freely available wildﬁre data for use by practitioners of ML methods.

show abstract

Section: Post-fire Regeneration Succession and Ecologymentioning

confidence: 99%

A review of machine learning applications in wildfire science and management

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Biodiversity and related ecosystem services issues resulted as connected, also, to studies about environmental disturbance phenomena, like fire. Many papers in rs+pheno studies analyzed the role of wildfires' behavior both as a driver of vegetation recovery patterns [101][102][103] and as influenced by fuel phenology and flammability [104,105]. In this latter case, a high potential exists for characterizing, classifying, and mapping fuel based on rs+pheno dynamics.…”

Section: Emerging Research Topicsmentioning

confidence: 99%

Text Mining in Remotely Sensed Phenology Studies: A Review on Research Development, Main Topics, and Emerging Issues

et al. 2019

View full text Add to dashboard Cite

As an interdisciplinary field of research, phenology is developing rapidly, and the contents of phenological research have become increasingly abundant. In addition, the potentiality of remote sensing technologies has largely contributed to the growth and complexity of this discipline, in terms of the scale of analysis, techniques of data processing, and a variety of topics. As a consequence, it is increasingly difficult for scientists to get a clear picture of remotely sensed phenology (rs+pheno) research. Bibliometric analysis is increasingly used for the study of a discipline and its conceptual dynamics. This review analyzed the last 40 years of publications in the rs+pheno field retrieved from the Scopus database; such publications were investigated by means of a text mining approach, both in terms of bibliographic and text data. Results demonstrated that rs+pheno research is exponentially growing through time; however, it is primarily considered a subset of remote sensing science rather than a branch of phenology. In this framework, in the last decade, agriculture is becoming more and more a standalone science in rs+pheno research, independently from other related topics, e.g., classification. On the contrary, forestry struggles to gain its thematic role in rs+pheno studies and remains strictly connected with climate change issues. Classification and mapping represent the major rs+pheno topic, together with the extraction and the analysis of phenological metrics, like the start of the growing season. To the contrary, forest ecophysiology, in terms of ecosystem respiration and net ecosystem exchange, results as the most relevant new topic, together with the use of the red edge band and SAR (Synthetic Aperture Radar) data in rs+pheno agricultural studies. Some niche emerging rs+pheno topics may be recognized in the ocean and arctic investigations linked to phytoplankton blooming and ice cover dynamics. The findings of this study might be applicable for planning and managing remotely sensed phenology research; scientists involved in such discipline might use this study as a reference to consider their research domain in a broader dynamical network.

show abstract

“…Equations (11) and (12) were iteratively applied until convergence. To perform optimal fuzzy clustering and to generate well separated and compact clusters, the Xie-Beni index was applied [58]:…”

Section: Clustering Of Dtw Distancesmentioning

confidence: 99%

“…Several studies focus on species-specific vegetation regrowth in different types of ecosystems such as conifers [3,4], mixed conifer/oaks [5], chaparral/maquis forests [6][7][8], and subalpine forests [9]. Most published research uses satellite images from the Landsat series [4,6,7] and Moderate Resolution Imaging Spectroradiometer (MODIS) [8,10,11] sensors due to their high temporal resolution and public access to archived data; however, radar and multisensor approaches were also applied successfully [5,12,13].…”

Section: Introductionmentioning

confidence: 99%

Neural-Network Time-Series Analysis of MODIS EVI for Post-Fire Vegetation Regrowth

Vasilakos

Tsekouras

Palaiologou

et al. 2018

IJGI

View full text Add to dashboard Cite

The time-series analysis of multi-temporal satellite data is widely used for vegetation regrowth after a wildfire event. Comparisons between pre- and post-fire conditions are the main method used to monitor ecosystem recovery. In the present study, we estimated wildfire disturbance by comparing actual post-fire time series of Moderate Resolution Imaging Spectroradiometer (MODIS) enhanced vegetation index (EVI) and simulated MODIS EVI based on an artificial neural network assuming no wildfire occurrence. Then, we calculated the similarity of these responses for all sampling sites by applying a dynamic time warping technique. Finally, we applied multidimensional scaling to the warping distances and an optimal fuzzy clustering to identify unique patterns in vegetation recovery. According to the results, artificial neural networks performed adequately, while dynamic time warping and the proposed multidimensional scaling along with the optimal fuzzy clustering provided consistent results regarding vegetation response. For the first two years after the wildfire, medium-high- to high-severity burnt sites were dominated by oaks at elevations greater than 200 m, and presented a clustered (predominant) response of revegetation compared to other sites.

show abstract

Indicator-based assessment of post-fire recovery dynamics using satellite NDVI time-series

Cited by 54 publications

References 71 publications

A review of machine learning applications in wildfire science and management

A review of machine learning applications in wildfire science and management

Text Mining in Remotely Sensed Phenology Studies: A Review on Research Development, Main Topics, and Emerging Issues

Neural-Network Time-Series Analysis of MODIS EVI for Post-Fire Vegetation Regrowth

Contact Info

Product

Resources

About