Bushra Praveen

Bio: Bushra Praveen is an academic researcher from Indian Institute of Technology Indore. The author has contributed to research in topics: Agriculture & Climate change. The author has an hindex of 6, co-authored 11 publications receiving 165 citations.

Analyzing trend and forecasting of rainfall changes in India using non-parametrical and machine learning approaches.

Abstract: This study analyzes and forecasts the long-term Spatio-temporal changes in rainfall using the data from 1901 to 2015 across India at meteorological divisional level. The Pettitt test was employed to detect the abrupt change point in time frame, while the Mann-Kendall (MK) test and Sen's Innovative trend analysis were performed to analyze the rainfall trend. The Artificial Neural Network-Multilayer Perceptron (ANN-MLP) was employed to forecast the upcoming 15 years rainfall across India. We mapped the rainfall trend pattern for whole country by using the geo-statistical technique like Kriging in ArcGIS environment. Results show that the most of the meteorological divisions exhibited significant negative trend of rainfall in annual and seasonal scales, except seven divisions during. Out of 17 divisions, 11 divisions recorded noteworthy rainfall declining trend for the monsoon season at 0.05% significance level, while the insignificant negative trend of rainfall was detected for the winter and pre-monsoon seasons. Furthermore, the significant negative trend (-8.5) was recorded for overall annual rainfall. Based on the findings of change detection, the most probable year of change detection was occurred primarily after 1960 for most of the meteorological stations. The increasing rainfall trend had observed during the period 1901-1950, while a significant decline rainfall was detected after 1951. The rainfall forecast for upcoming 15 years for all the meteorological divisions' also exhibit a significant decline in the rainfall. The results derived from ECMWF ERA5 reanalysis data exhibit that increasing/decreasing precipitation convective rate, elevated low cloud cover and inadequate vertically integrated moisture divergence might have influenced on change of rainfall in India. Findings of the study have some implications in water resources management considering the limited availability of water resources and increase in the future water demand.

Land-Use Land-Cover Classification by Machine Learning Classifiers for Satellite Observations—A Review

Abstract: 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.

Land-Use and Land-Cover Classification Using a Human Group-Based Particle Swarm Optimization Algorithm with an LSTM Classifier on Hybrid Pre-Processing Remote-Sensing Images

Abstract: Land-use and land-cover (LULC) classification using remote sensing imagery plays a vital role in many environment modeling and land-use inventories. In this study, a hybrid feature optimization algorithm along with a deep learning classifier is proposed to improve the performance of LULC classification, helping to predict wildlife habitat, deteriorating environmental quality, haphazard elements, etc. LULC classification is assessed using Sat 4, Sat 6 and Eurosat datasets. After the selection of remote-sensing images, normalization and histogram equalization methods are used to improve the quality of the images. Then, a hybrid optimization is accomplished by using the local Gabor binary pattern histogram sequence (LGBPHS), the histogram of oriented gradient (HOG) and Haralick texture features, for the feature extraction from the selected images. The benefits of this hybrid optimization are a high discriminative power and invariance to color and grayscale images. Next, a human group-based particle swarm optimization (PSO) algorithm is applied to select the optimal features, whose benefits are a fast convergence rate and ease of implementation. After selecting the optimal feature values, a long short-term memory (LSTM) network is utilized to classify the LULC classes. Experimental results showed that the human group-based PSO algorithm with a LSTM classifier effectively well differentiates the LULC classes in terms of classification accuracy, recall and precision. A maximum improvement of 6.03% on Sat 4 and 7.17% on Sat 6 in LULC classification is reached when the proposed human group-based PSO with LSTM is compared to individual LSTM, PSO with LSTM, and Human Group Optimization (HGO) with LSTM. Moreover, an improvement of 2.56% in accuracy is achieved, compared to the existing models, GoogleNet, Visual Geometric Group (VGG), AlexNet, ConvNet, when the proposed method is applied.

Analysing the trend of rainfall in Asir region of Saudi Arabia using the family of Mann-Kendall tests, innovative trend analysis, and detrended fluctuation analysis

Abstract: The present study is designed to analyse the annual rainfall variability and trend in 30 meteorological stations of the Asir region for the period of 1970–2017 using the Mann-Kendall (MK) test, Modified Mann-Kendall (MMK) test, trend free pre-whitening Mann-Kendall (TFPW MK) test, and the innovative trend analysis (ITA). A comparative study among the trend detection techniques was performed using the correlation coefficient. The future rainfall trend based on the historical rainfall pattern was investigated by using detrended fluctuation analysis (DFA). Results of the MK test showed that 20 stations in the study area observed a negative trend, and out of these, nine stations had significant negative trends at the significance level of 0.01. The findings of the MMK test showed that 23 stations recorded negative trends, and out of these, 18 stations had significant negative trends at the significance level of 0.01. Based on the findings of the TFPW-MK test, 21 stations observed a negative trend, and among these, 10 stations had significant negative trends at the significance of 0.01. ITA detected 25 stations observing a negative trend, and out of these, 18 stations had significant negative trends at the significance level of 0.01. Based on the findings of the tests and their performance, the MMK test appeared as the best performing technique among the MK test family, while ITA appeared as the best trend detection technique among the four techniques because it outperformed (p < 0.01) the others. Results of DFA showed that 23 stations (10 were significant) had recorded declining future rainfall trends based on past trends. The results of the present study would help the planners and policy makers to make accurate and easy decisions on irrigation, climatic, and water resource management in the Asir region of Saudi Arabia.