Monitoring Forest Change in the Amazon Using Multi-Temporal Remote Sensing Data and Machine Learning Classification on Google Earth Engine

Abstract

Deforestation causes diverse and profound consequences for the environment and species. Direct or indirect effects can be related to climate change, biodiversity loss, soil erosion, floods, landslides, etc. As such a significant process, timely and continuous monitoring of forest dynamics is important, to constantly follow existing policies and develop new mitigation measures. The present work had the aim of mapping and monitoring the forest change from 2000 to 2019 and of simulating the future forest development of a rainforest region located in the Pará state, Brazil. The land cover dynamics were mapped at five-year intervals based on a supervised classification model deployed on the cloud processing platform Google Earth Engine. Besides the benefits of reduced computational time, the service is coupled with a vast data catalogue providing useful access to global products, such as multispectral images of the missions Landsat five, seven, eight and Sentinel-2. The validation procedures were done through photointerpretation of high-resolution panchromatic images obtained from CBERS (China–Brazil Earth Resources Satellite). The more than satisfactory results allowed an estimation of peak deforestation rates for the period 2000–2006; for the period 2006–2015, a significant decrease and stabilization, followed by a slight increase till 2019. Based on the derived trends a forest dynamics was simulated for the period 2019–2028, estimating a decrease in the deforestation rate. These results demonstrate that such a fusion of satellite observations, machine learning, and cloud processing, benefits the analysis of the forest dynamics and can provide useful information for the development of forest policies.

Machine Learning Classification of Mediterranean Forest Habitats in Google Earth Engine Based on Seasonal Sentinel-2 Time-Series and Input Image Composition Optimisation

“…Moreover, we tested either a composition with these three best indices and a composition with all indices, highlighting that, for classification purposes, a correct choice of VIs is needed and should be preferred to the mere addition of derived indices. Concerning the classification process, the choice of the three adopted classifiers was in line with the findings of the review of Taminia et al [14], who reported RF, CART, and SVM as those which have been most adopted in previous GEE works (97,26, and 21 published papers, respectively). Concerning the accuracy results, RF proved to be the best solution, in agreement with Rodriguez-Galiano et al [123], who defined RF as being superior to other classifiers.…”

“…The GEE environment integrates several different classifiers. We compared the performance of three of them, chosen according to their wide use and reliability in LC classification [11,14,86,[97][98][99][100][101]: random forest (RF), classification and regression tree (CART), and support vector machine (SVM).…”

Classification of Nemoral Forests with Fusion of Multi-Temporal Sentinel-1 and 2 Data

“…Adding a temporal dimension, the fusion of multi-temporal acquisitions of RS data provide opportunities to detect changes in, for example, forest cover over time [34]. However, in the nemoral forest zone, multi-temporal data may further detect seasonal variation in spectral signature and radiometric backscatter specific to e.g., individual tree species or forest types.…”

Tropical Forest Monitoring: Challenges and Recent Progress in Research

“…These studies can be potentially crucial for improvements of emissions estimates -such as [37]. A number of studies were identified which present platforms that can promote and improve public access to information, and these platforms have also proved to be crucial for forest monitoring efforts [38,39]. Near-real-time (NRT) forest monitoring studies were less represented in the results of the literature search, and some countries did not have a single study in this category.…”