Since clean water is well known as one of the crucial sources that all living things need in their daily lives, the demand for clean freshwater nowadays has increased. However, water quality is slowly deteriorating due to anthropogenic and natural sources of pollution and contamination. Therefore, this study aims to develop artificial neural network (ANN) models to predict six different water quality parameters in the Langat River, Malaysia. Moreover, an application (app) equipped with a graphical user interface (GUI) was designed and developed to conduct real-time prediction of the water quality parameters by using real-time data as inputs together with the ANN models. As for the results, all of the ANN models achieved high coefficients of determination (R²), which were between 0.9906 and 0.9998, as well as between 0.8797 and 0.9972 for training and testing datasets, respectively. The developed app successfully predicted the outcome based on the run models. The implementation of a GUI-based app in this study enables a simpler and more trouble-free workflow in predicting water quality parameters. By eliminating sophisticated programming subroutines, the prediction process becomes accessible to more people, especially on-site operators and trainees.

In this study, we improved and adapted existing signal processing methods on vast geomagnetic field data to investigate the correlations between various earthquake properties and characteristics of possible geomagnetic precursors. The data from 10 magnetometer stations were utilized to detect precursory ultra-low frequency emission and estimate the source direction for 34 earthquakes occurring between the year 2007–2016 in Southeast Asia, East Asia, and South America regions. As a result, possible precursors of 20 earthquakes were identified (58.82% detection rate). Weak correlations were obtained when all precursors were considered. However, statistically significant and strong linear correlations ($r\ge 0.60,p<0.05$) were found when the precursors from two closely located stations in Japan (Onagawa (ONW) and Tohno (TNO)) were exclusively investigated. For these stations, it was found that the lead time of the precursor is strongly (or very strongly) correlated with the earthquake magnitude, the local seismicity index, and the hypocentral depth. In addition, the error percentage of the estimated direction showed a strong correlation with the hypocentral depth. It is concluded that, when the study area is restricted to a specific location, the earthquake properties are more likely to have correlations with several characteristics of the possible precursors.

Recent studies reported that the diurnal variation of the geomagnetic field exhibited anomalous characteristics several months before earthquakes (EQs). However, the statistical significance of such anomalies detected using the diurnal variation range ratio (DVRR) method still requires verification as only a limited number of EQs occurring in certain seismoactive zones were included. In this study, the DVRR method was employed in conjunction with the superposed epoch analysis (SEA) to perform a large-scale study. A total of 157 EQs that occurred between 2000 and 2019 were investigated using vast geomagnetic field data collected from 92 ground-based magnetometer stations spread across multiple global regions. The case study conducted on the May 13, 2011, M6.1 Honshu (Japan) EQ showed that the diurnal variation of the vertical geomagnetic component disappeared around a week before the EQ. The case study also demonstrated the effectiveness of the DVRR method in minimizing solar disturbance influences, further proving that the observed anomalies were not caused by the Sun. The subsequent SEA revealed statistically significant increases in anomaly counts before the occurrence of EQs for all three geomagnetic components. The number of anomalies gradually increased approaching the day of EQs with temporal lags between the components. Furthermore, a control group analysis confirmed the findings by demonstrating that the increases were not coincidental and several explanations have been suggested, focusing primarily on the emergence and generation mechanisms of the anomalies. Results from this study showed that the anomalies were significant and were potentially precursors to the succeeding EQs.

ABSTRACT Road deterioration due to potholes has a significant impact on traffic safety and infrastructure maintenance, highlighting the need for detection systems that combine precision with real-time capabilities. Although YOLO-based algorithms have been widely adopted for their speed and efficiency in object detection, achieving a balance between high accuracy and low inference time remains a challenge, particularly in scenarios involving small objects and complex features. This study introduces YOLOv7-C3ECA-DSA, an improved YOLOv7 architecture designed to address these limitations. The model incorporates Cross-Stage Enhanced Channel Attention (C3ECA) blocks in the backbone network and Depthwise Shuffle Attention (DSA) in the detection head to enhance feature learning and boundary detection, achieving high detection accuracy and real-time inference capabilities. The experimental results demonstrate that YOLOv7-C3ECA-DSA achieves an mAP0.5 of 85.3% with an inference time of 10.9 ms, outperforming the prior methods. The proposed model also performs well under adverse vision conditions such as night and rain. However, the model performance may be limited in severe environmental conditions, such as low-contrast surfaces or heavily obscured potholes. Despite these limitations, the research significantly advances real-time pothole detection by striking an optimal balance between computational efficiency and detection accuracy. The findings underscore the effectiveness of YOLOv7-C3ECA-DSA in addressing practical challenges in real-time infrastructure monitoring, making it suitable for scalable deployment in autonomous vehicle systems and road maintenance applications.