Rapid and uncontrolled population growth along with economic and industrial development, especially in developing countries during the late twentieth and early twenty-first centuries, have increased the rate of land-use/land-cover (LULC) change many times. Since quantitative assessment of changes in LULC is one of the most efficient means to understand and manage the land transformation, there is a need to examine the accuracy of different algorithms for LULC mapping in order to identify the best classifier for further applications of earth observations. In this article, six machine-learning algorithms, namely random forest (RF), support vector machine (SVM), artificial neural network (ANN), fuzzy adaptive resonance theory-supervised predictive mapping (Fuzzy ARTMAP), spectral angle mapper (SAM) and Mahalanobis distance (MD) were examined. Accuracy assessment was performed by using Kappa coefficient, receiver operational curve (RoC), index-based validation and root mean square error (RMSE). Results of Kappa coefficient show that all the classifiers have a similar accuracy level with minor variation, but the RF algorithm has the highest accuracy of 0.89 and the MD algorithm (parametric classifier) has the least accuracy of 0.82. In addition, the index-based LULC and visual cross-validation show that the RF algorithm (correlations between RF and normalised differentiation water index, normalised differentiation vegetation index and normalised differentiation built-up index are 0.96, 0.99 and 1, respectively, at 0.05 level of significance) has the highest accuracy level in comparison to the other classifiers adopted. Findings from the literature also proved that ANN and RF algorithms are the best LULC classifiers, although a non-parametric classifier like SAM (Kappa coefficient 0.84; area under curve (AUC) 0.85) has a better and consistent accuracy level than the other machine-learning algorithms. Finally, this review concludes that the RF algorithm is the best machine-learning LULC classifier, among the six examined algorithms although it is necessary to further test the RF algorithm in different morphoclimatic conditions in the future.

Flood is considered one of the most dangerous natural disasters among all-natural disasters. Prediction of flood susceptible areas is a primary task for adopting management plans for minimizing the colossal failure of the flood. The present work intended to identify the flood susceptible areas by using multi Machine Learning (ML) algorithms based on fourteen flood conditioning parameters in Tangon river basin of Indo-Bangladesh. Apart from statistical tests (AUC of ROC, Friedman test, Wilcoxon Signed Rank Test), Index of Flood Vulnerability (IFV) using field data-sets and 2 D flood simulation model using HEC-RAS software were used to validate the flood susceptibility models. The ML models predicted 4.95% to 17.53% area comes under a very high flood susceptible zone. Support vector machine model best suit model compared to all models. Sensitivity analysis of the model clarified that geology, rainfall, elevation, and drainage factors played a dominant role for determining the model.

Amidst global shifts in land use patterns due to urbanization, this study focuses on the rapid land use and land cover (LULC) changes in Midnapore City during the periods 2003–2014 and 2014–2024. The study employs Landsat 5 and 8 imagery with 30 m spatial resolution which were processed through Maximum Likelihood Classifier (MLC) algorithms. The results were attained through ArcGIS 10.2.2 and ERDAS IMAGINE 2014 software, with ground-truth validation using data from 117, 111, and 116 points for 2024, 2014, and 2003, respectively. For the validation, the kappa coefficient was calculated and achieved 87.3%, 88.1%, and 81.7% for 2024, 2014, and 2003, indicating substantial accuracy. Using statistical measures such as change matrix union, binary logistic regression, and correlation matrix analysis applied to classified LULC outputs and spatial drivers, the research highlights significant transformations in the region. The study reveals significant transformations, notably the conversion of 77% of forest areas and 5% of fallow land to built-up land. The increased rate of agricultural land conversion to built-up areas is evident after 2014, indicating rapid urban growth. These factors led to the reduction of LULC classes possessing substantial ecological value like forests and scrub lands which are becoming more accessible due to the increasing population. The results point out the drastic alteration of these developments and recommend a planning approach responsive to environmental needs for safeguarded ecological impacts. The research highlights the importance of reforestation, preservation of water bodies, and socio-economic surveillance in fostering urban management and sustainable development in Midnapore City.