<p>Deforestation remains one of the largest contributors to global greenhouse emissions. Despite the efforts in monitoring forest change, there is still a lack of pan-tropical spatially-explicit data informing the subsequent land cover (LC) changes over deforested areas (also known as post-loss LC). Based on this premise, this research focuses on predicting post-loss LC over deforested areas as detected by Terra-i, an early warning system of pantropical forest change providing alerts every 16-days from 2004 to present at spatial resolution of 250 m. A supervised deep neural network model suited to extract spatio-temporal patterns from dense earth observation time series data was leveraged in this work by using 16-day MODIS images of 2015. The model was trained according to nine labelled datasets representing different number of LC classes and complexity. These datasets were generated from pre-existing global LC maps with a native spatial resolution ranging from 100 m to 500 m. The effectiveness of the trained models in producing accurate predictions of post-loss LC was assessed over the Amazon region, the largest continuous region of tropical forest in the world. A two-stage assessment approach was conducted to determine the most suitable labelled datasets to predict post-loss LC over Terra-i&#8217;s areas. For the first stage, traditional metrics for the assessment of the quality of LC thematic data &#8212; e.g. overall accuracy, per-class mapping accuracy, area (or quantity) disagreement and allocation disagreement &#8212; were computed according to the test partitions from the labelled datasets. A second stage consisted in using the trained models in 2015 to make predictions for all available years of MODIS satellite imagery, from 2001 to 2018, across seven representative areas distributed in the Amazon. The observed LC predictions were masked using annual aggregated data of Terra-i from 2004 to 2010. The post-LC data by trained model, which represents a given labelled dataset, was verified by i) visualising the temporal and spatial distribution of the most frequent subsequent LC changes; and ii) comparing with Mapbiomas Amazonia, a regional-tuned multi-temporal LC dataset from 2000 to 2017 for the whole Amazon. The results showed that one out of the nine labelled datasets allowed the supervised deep learning model to produce reasonable spatial predictions and classification accuracies (overall accuracy of 86.36&#177;0.64, area disagreement of 5.34&#177;0.39 and allocation disagreement of 8.31&#177;0.64) according to the test partition data. Moreover, the trained model provided similar patterns of post-loss LC as informed by the Mapbiomas dataset. Due to the nature of the model (i.e. neural network) and input data (i.e. global), it is expected the model is scalable to other pantropical areas. The insights and products derived throughout this study are targeted to reduce current uncertainties and challenges in the calculation of global and regional drivers and impacts of deforestation in tropical forests and landscapes.</p>
<p>Making assets in scientific research <strong>Findable, Accessible, Interoperable and Reusable (FAIR)</strong> is still overwhelming for many scientists. When considered as an afterthought, FAIR research is indeed challenging, and we argue that its implementation is by far much easier when considered at an early stage and focusing on improving the researchers' day to day work practices. One key aspect is to bundle all the research artefacts in a FAIR Research Object (RO) using RoHub (https://reliance.rohub.org/), a Research Object management platform that enables researchers to collaboratively manage, share and preserve their research work (data, software, workflows, models, presentations, videos, articles, etc.). RoHub implements the full RO model and paradigm: resources associated to a particular research work are aggregated into a single FAIR digital object, and metadata relevant for understanding and interpreting the content is represented as semantic metadata that are user and machine readable. This approach provides the technical basis for implementing FAIR executable notebooks: the data and the computational environment can be &#8220;linked&#8221; to one or several FAIR notebooks that can then be executed via EGI Binder Service with scalable compute and storage capabilities. However, the need for defining clear practises for writing and publishing FAIR notebooks that can be reused to build upon new research has quickly arised. This is where a community of practice is required. The <strong>Environmental Data Science Book (or EDS Book)</strong> is a pan-european community-driven resource hosted on GitHub and powered by Jupyter Book. EDS Book provides practical guidelines and templates that help to translate research outputs into curated, interactive, shareable and reproducible executable notebooks. The quality of the FAIR notebooks is ensured by a collaborative and transparent reviewing process supported by GitHub related technologies. This approach provides immediate benefits for those who adopt it and can feed fruitful discussions to better define a reward system that would benefit Science and scientific communities. All the resources needed for understanding and executing the notebook are gathered into an executable Research Object in RoHub. To date, the community has successfully published ten FAIR notebooks covering a wide range of topics in environmental data science. The notebooks consume open-source python libraries e.g. <em>intake</em>, <em>iris</em>, <em>xarray</em>, <em>hvplot</em> for fetching, processing and interactively visualising environmental research.&#160; While these notebooks are currently python-based, EDS Book supports other programming languages such as R and Julia, and we are aiming at engaging with computational notebooks communities alike towards improving the research practices in environmental science.</p>
The numerous benefits of Open Science (OS) and of the four FAIR foundational principles -Findable, Accessible, Interoperable and Reusable- are increasingly valued in academia, although what OS and FAIR entail is still largely misunderstood. In such conditions putting in practice OS and applying the FAIR principles is challenging and underrated. However, realising OS is perfectly within grasp provided that an infrastructure supporting the management of the research lifecycle is available. RoHub is precisely a Research Object (RO) management platform implementing three complementary technologies: Research Objects, Data Cubes and Artificial Intelligence-based Text Mining services. RoHub enables researchers to collaboratively manage, share and preserve their research while they are still working on it (rather than after the work is finished). In this paper, three communities from Earth Sciences, namely Geohazards, Sea Monitoring and Climate Change, demonstrate how RoHub helped them to understand each other and to work openly, and more importantly how communities of practice play an important role in facilitating reuse and interdisciplinary collaboration. These findings are illustrated with several use cases from these various communities.
<p>Building change detection based on remote sensing imagery is a key task for land management and planning e.g., detection of illegal settlements, updating land records and disaster response. Under the post- classification comparison approach, this research aimed to evaluate the feasibility of several classification algorithms to identify and capture buildings and their change between two time steps using very-high resolution images (<1 m/pixel) across rural areas and urban/rural perimeter boundaries. Through an App implemented on the Google Earth Engine (GEE) platform, we selected two study areas in Colombia with different images and input data. In total, eight traditional classification algorithms, three unsupervised (K-means, X-Means y Cascade K-Means) and five supervised (Random Forest, Support Vector Machine, Naive Bayes, GMO maximum Entropy and Minimum distance) available at GEE were trained. Additionally, a deep neural network named Feature Pyramid Networks (FPN) was added and trained using a pre-trained model, EfficientNetB3 model. Three evaluation zones per study area were proposed to quantify the performance of the algorithms through the Intersection over Union (IoU) metric. This metric, with a range between 0 and 1, represents the degree of overlapping between two regions, where the higher agreement the higher IoU values. The results indicate that the models configured with the FPN network have the best performance followed by the traditional supervised algorithms. The performance differences were specific to the study area. For the rural area, the best FPN configuration obtained an IoU averaged for both time steps of 0.4, being this four times higher than the best supervised model, Support Vector Machines using a linear kernel with an average IoU of 0.1. Regarding the setting of urban/rural perimeter boundaries, this difference was less marked, having an average IoU of 0.53 in comparison to 0.38 obtained by the best supervised classification model, in this case Random Forest. The results are relevant for institutions tracking the dynamics of building areas from cloud computing platfo future assessments of classifiers in likewise platforms in other contexts.</p>
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.