This study applies machine learning methods such as Decision Tree (CART) and Random Forest to classify drought intensity based on meteorological data. The goal of the study was to evaluate the effectiveness of these methods for drought classification and their use in water resource management and agriculture. The methodology involved using two machine learning models that analyzed temperature and humidity indicators, as well as wind speed indicators. The models were trained and tested on real meteorological data to assess their accuracy and identify key factors affecting predictions. Results showed that the Random Forest model achieved the highest accuracy of 94.4% when analyzing temperature and humidity indicators, while the Decision Tree (CART) achieved an accuracy of 93.2%. When analyzing wind speed indicators, the models’ accuracies were 91.3% and 93.0%, respectively. Feature importance revealed that atmospheric pressure, temperature at 2 m, and wind speed are key factors influencing drought intensity. One of the study’s limitations was the insufficient amount of data for high drought levels (classes 4 and 5), indicating the need for further data collection. The innovation of this study lies in the integration of various meteorological parameters to build drought classification models, achieving high prediction accuracy. Unlike previous studies, our approach demonstrates that using a wide range of meteorological data can significantly improve drought classification accuracy. Significant findings include the necessity to expand the dataset and integrate additional climatic parameters to improve models and enhance their reliability.

One significant importance of street vending in South Africa is its role in providing livelihoods and economic opportunities, especially for marginalized and vulnerable populations. However, Street vendors, particularly those selling agricultural commodities, face numerous challenges. Street vending in Moletjie Mmotong is a vital source of income and employment, offering affordable goods and services, including food, clothing, and household items. One potential solution is online selling, but there is limited knowledge about it in the informal sector. This study aims to analyze the factors affecting street vendors’ willingness to sell fruits and vegetables online in Moletjie Mmotong under Polokwane Municipality. Data was collected from 60 street vendors using a questionnaire and simple random sampling. Descriptive statistics identified and described the socio-economic characteristics of the vendors, while a binary logistic regression model analyzed the factors influencing their willingness to sell online. The study found that age, education level, gender, household size, and access to online selling information significantly influenced their willingness to sell online. The findings highlight the potential benefits of online selling for street vendors, such as increased sales and a broader customer base. The study recommends that governments provide training and workshops on online selling, develop educational programs, distribute educational materials, and create marketing strategies to support street vendors in transitioning to online platforms.

This study investigated the changing land use patterns and their impacts on ecosystem in the Teesta River Basin of northwestern Bangladesh. Although anthropocentric land use patterns, including agricultural land use, settlements, built areas, and waterbody loss, have been increasing in the Nilphamari district, by negatively affecting local ecosystems, they have not been identified by prior research. Limitations of contemporary literature motivated me to work on this crucial ground in the Teesta River Basin in Northwestern Bangladesh. This study applied a mixed research approach to identify the study objectives. Firstly, the land use and land cover (LULC) changes which occurred between 2000 and 2020 were detected using satellite imagery and supervised classification method. In addition to the detection of LULC changes, the study explored the people’s perceptions and experiences about the ecosystem changes resulted from the LULC changes over the last 20 years, conducting stakeholders’ consultations and household surveys utilizing a semi-structured questionnaire. The findings indicated that waterbodies in Nilphamari district have significantly decreased from 378 km² in 2000 to 181 km² in 2020. In the same way, the vegetation coverage has reduced 187 km² between the years 2000 and 2020. On the contrary, agricultural lands (croplands) have increased from 595 km² to 905 km² and settlements have increased from 81 km² to 206 km² between the years 2000 and 2020. From the chi-square test, it was found a significant association between ecosystem change and biodiversity loss. It was further identified that waterbody decreases have significant impacts on aquatic ecosystems. The results of this study also indicated that due to the introduction of foreign tree species, local and native species have been significantly decreasing over the time. This study emphasizes the non-anthropocentric and inclusive land use policy implications for protecting life on land and preserving the aquatic ecosystem in Bangladesh.

In this paper, we assess the results of experiment with different machine learning algorithms for the data classification on the basis of accuracy, precision, recall and F1-Score metrics. We collected metrics like Accuracy, F1-Score, Precision, and Recall: From the Neural Network model, it produced the highest Accuracy of 0.129526 also highest F1-Score of 0.118785, showing that it has the correct balance of precision and recall ratio that can pick up important patterns from the dataset. Random Forest was not much behind with an accuracy of 0.128119 and highest precision score of 0.118553 knit a great ability for handling relations in large dataset but with slightly lower recall in comparison with Neural Network. This ranked the Decision Tree model at number three with a 0.111792, Accuracy Score while its Recall score showed it can predict true positives better than Support Vector Machine (SVM), although it predicts more of the positives than it actually is a majority of the times. SVM ranked fourth, with accuracy of 0.095465 and F1-Score of 0.067861, the figure showing difficulty in classification of associated classes. Finally, the K-Neighbors model took the 6th place, with the predetermined accuracy of 0.065531 and the unsatisfactory results with the precision and recall indicating the problems of this algorithm in classification. We found out that Neural Networks and Random Forests are the best algorithms for this classification task, while K-Neighbors is far much inferior than the other classifiers.

This study conducts a comparative analysis of various machine learning and deep learning models for predicting order quantities in supply chain tiers. The models employed include XGBoost, Random Forest, CNN-BiLSTM, Linear Regression, Support Vector Regression (SVR), K-Nearest Neighbors (KNN), Multi-Layer Perceptron (MLP), Recurrent Neural Network (RNN), Bidirectional LSTM (BiLSTM), Bidirectional GRU (BiGRU), Conv1D-BiLSTM, Attention-LSTM, Transformer, and LSTM-CNN hybrid models. Experimental results show that the XGBoost, Random Forest, CNN-BiLSTM, and MLP models exhibit superior predictive performance. In particular, the XGBoost model demonstrates the best results across all performance metrics, attributed to its effective learning of complex data patterns and variable interactions. Although the KNN model also shows perfect predictions with zero error values, this indicates a need for further review of data processing procedures or model validation methods. Conversely, the BiLSTM, BiGRU, and Transformer models exhibit relatively lower performance. Models with moderate performance include Linear Regression, RNN, Conv1D-BiLSTM, Attention-LSTM, and the LSTM-CNN hybrid model, all displaying relatively higher errors and lower coefficients of determination (R²). As a result, tree-based models (XGBoost, Random Forest) and certain deep learning models like CNN-BiLSTM are found to be effective for predicting order quantities in supply chain tiers. In contrast, RNN-based models (BiLSTM, BiGRU) and the Transformer show relatively lower predictive power. Based on these results, we suggest that tree-based models and CNN-based deep learning models should be prioritized when selecting predictive models in practical applications.

This study employed the theory of planned behavior to examine how green urban spaces influence walking behaviors, with a focus on Chongqing’s Jiefangbei Pedestrian Street. Using structural equation modelling to analyse survey data from 401 respondents, this study assessed the relationships between attitudes, subjective norms, perceived behavioral control, walking intentions, and actions. The results revealed that attitudes toward walking (β = 0.335, p < 0.001) and subjective norms (β = 0.221, p < 0.001) significantly predict walking intentions, which strongly determine actual walking behavior (β = 0.379, p < 0.001). Moreover, perceived behavioral control exerts a direct significant impact on walking actions (β = 0.332, p < 0.001), illustrating that both environmental and social factors are crucial in promoting pedestrian activity. These findings suggest that enhancing the appeal and accessibility of urban green spaces can significantly encourage walking, providing valuable insights for urban planning and public health policy. This study can guide city planners and health professionals in creating more walkable and health-conducive urban environments.