Assessment of k-Nearest Neighbor and Random Forest Classifiers for Mapping Forest Fire Areas in Central Portugal Using Landsat-8, Sentinel-2, and Terra Imagery

Deep learning-based burned forest areas mapping via Sentinel-2 imagery: a comparative study

In order to evaluate the effects of forest fires on the dynamics of the function and structure of ecosystems, it is necessary to determine burned forest areas with high accuracy, effectively, economically, and practically using satellite images. Extraction of burned forest areas utilizing high-resolution satellite images and image classification algorithms and assessing the successfulness of varied classification algorithms has become a prominent research field. This study aims to indicate on the capability of the deep learning-based Stacked Autoencoders method for the burned forest areas mapping from Sentinel-2 satellite images. The Stacked Autoencoders, used in this study as an unsupervised learning method, were compared qualitatively and quantitatively with frequently used supervised learning algorithms (k-Nearest Neighbors (k-NN), Subspaced k-NN, Support Vector Machines, Random Forest, Bagged Decision Tree, Naive Bayes, Linear Discriminant Analysis) on two distinct burnt forest zones. By selecting burned forest zones with contrasting structural characteristics from one another, an objective assessment was achieved. Manually digitized burned areas from Sentinel-2 satellite images were utilized for accuracy assessment. For comparison, different classification performance and quality metrics (Overall Accuracy, Mean Squared Error, Correlation Coefficient, Structural Similarity Index Measure, Peak Signal-to-Noise Ratio, Universal Image Quality Index, and KAPPA metrics) were used. In addition, whether the Stacked Autoencoders method produces consistent results was examined through boxplots. In terms of both quantitative and qualitative analysis, the Stacked Autoencoders method showed the highest accuracy values.

Optimum supervised classification algorithm identification by investigating PlanetScope and Skysat multispectral satellite data of Covid lockdown

This research identifies the optimum supervised classification algorithm based on modeling Covid 19 lockdown situations all around the World. As the deadly Covid 19 viruses suddenly stopped the fast-moving World. All the commercial and noncommercial activities suddenly stop for an uncertain period during 2020-2021. In this work, object-based image classification approaches have been used to compare pre-Covid and post-Covid (at the time lockdown) images of the study area. These study areas are Washington DC, USA, Sao Paulo, Brazil, Cairo, Egypt, Afghanistan/Iran border, and Beijing, China. All the study areas possess different geographical conditions but have a similar situation of Covid 19 lockdowns. Six supervised image classification techniques are known as Parallelepiped classification (PPC), Minimum distance classification (MDC), Mahalanobis distance classification (MaDC), Maximum likelihood classification (MLC), Spectral angle mapper classification (SAMC) and Spectral information divergence classification (SIDC) are used to classify the satellite data of the study area. Thus based on classification results and statistical features, it has been observed that PPChas obtained the least significant results. In contrast, the most reliable results and highest classification accuracies are obtained through MDC, MaDC, and MLCclassification algorithms.

Machine learning algorithm for estimating karst rocky desertification in a peak-cluster depression basin in southwest Guangxi, China

Karst rocky desertification (KRD) has become one of the most serious ecological and environmental problems in karst areas. At present, mapping KRD with a high accuracy and on a large scale is still a difficult problem in the control of KRD. In this study, a random forest (RF) based on maximum information coefficient and correlation coefficient feature selection is proposed to predict KRD. Nine predictors stood out as feature factors to estimate KRD. Rock exposure was the most important predictor, followed by fractional vegetation cover for the prediction of KRD processes. The kappa and classification accuracy indexes were to evaluate the performance of the model. We recorded overall accuracy rate and kappa index values of 94.7% and 0.92 for the testing datasets respectively. The RF model was then used to predict the KRD in 2001, 2011, 2016, and 2020, and it was found that the KRD in the study area has exhibited a positive trend of improvement. Therefore, the use of multisource remote sensing data combined with the RF model can obtain better prediction results of KRD, thereby providing a new idea for large-scale estimation of the KRD in peak-cluster depression.