Search

A continuous supply of electricity is necessary to maintain an acceptable standard of life, and the power distribution system's overhead line components play a crucial role in this matter. In Pakistan, identifying defective parts often necessitates human involvement. An unmanned aerial vehicle was used to gather a collection of 10,343 photos to automate this procedure. Using supervised and unsupervised machine learning methods, a number of automated anomaly detection systems were created. Support vector machine, random forest, VGG16, and ResNet50 were used as supervised machine learning models, and a convolutional auto‐encoder was used as the unsupervised machine learning model. VGG16 achieved the best accuracy of 99.00% while random forest achieved the worst accuracy of 72.49%. The convolutional auto‐encoder was successful in distinguishing between normal and abnormal components. The aforementioned machine learning models can be put on unmanned aerial vehicles to immediately identify defective parts. [ABSTRACT FROM AUTHOR]

This article investigates the temporal analysis of billion tree tsunami forests in Garhi Chandan area of Pakistan based on three supervised methods, namely random forest algorithm (RFA), principal component analysis (PCA) combined RFA and support vector machine (SVM). As a first step, the Sentinel-2 and Landsat-8 data fusion is performed to enhance the spatial resolution of the data to 10 m. The overlapping features in the data may compromise the classification accuracy, thus, to overcome this limitation, PCA is utilized. As a second step, classification is performed using RFA, PCA-RFA and SVM methods by using the data of the years 2016 and 2023. The change map analysis is done by using the aforementioned methods. As a next step, ground data matching is performed for the classified samples using each method. Finally, by utilizing logistic regression, future prediction for the years 2028, 2030 and 2033 is performed. The PCA-RFA technique achieved the best overall accuracy of 95% with a Kappa hat score of 0.93. The second-best result is achieved by RFA classifier, with overall accuracy of 92% with a Kappa hat score of 0.92. SVM showed moderate matching with an overall accuracy of 72% with a Kappa hat score of 0.55. [ABSTRACT FROM AUTHOR]

Flashed over insulator faults are the most significant faults in high voltage line insulators. They are complicated to identify using traditional methods due to their labor-intensive nature. This study proposes a deep learning-based algorithm for detecting flashed over insulator faults in the real time. The algorithm is based on the Resnet 50 architecture, which has been shown to be effective for image classification tasks in the previous studies regarding image analysis. The algorithm is fast, robust and efficient, making it suitable for real-time applications. The algorithm is trained on a dataset of images of flashed over and non-flashed over insulators. This dataset was collected from various transmission lines and National Center of Robotics and Automation, which are located in Pakistan. For validating the effectiveness of the Resnet 50 algorithm, it was compared with the results obtained from the two other widely popular deep learning algorithms, Densenet 121 and VGG 16 (trained and validated on the same dataset). The results showed that the Resnet 50 was able to detect flashed over insulator faults with an accuracy of over 99%. Whereas the Densenet 121 and VGG 16 have achieved an accuracy of less than 51%. [ABSTRACT FROM AUTHOR]

Modern development in deep learning and computer vision techniques, intelligent transportation system (ITS) has emerged as a useful tool for building a traffic infrastructure in smart cities. Previously, several computer vision techniques have been proposed for vehicle recognition, which were limited in handling undisciplined, dense and laneless traffic conditions. Moreover, these frameworks did not incorporate many of the local vehicle configurations common in South Asian countries such as Pakistan, Bangladesh, and India. Considering the limitations of previous frameworks, this paper presents efficient vehicle detection and counting model for undisciplined conditions including dense and laneless traffic, occulusion cases and diverse range of local vehicles. A dataset of more than 2400 images of vehicles has been collected comprising of six new categories of local vehicles, and considering undisciplined traffic conditions to ensure robustness in vehicle detection and counting system. Transfer learning based technique has been used, using faster R-CNN model with Inception V2 as underlying architecture. The experimental results show a precision of 86.14% in terms of mAP. The work finds its application in South Asian contexts as more smart cities are formed in this region. The proposed framework will enable traffic monitoring with higher reliability, accuracy and granularity, contributing in having next-generation ITS. [ABSTRACT FROM AUTHOR]

Early detection of breast cancer is the most important area of mammography research at the moment. It is critical to use computer-aided diagnosis to screen for and prevent breast cancer. In this study, the effectiveness of cutting-edge deep segmentation models for mammography in the detection of breast tumors was investigated. A medical images dataset was compiled and annotated at Lady Reading Hospital, one of the largest teaching hospitals in Pakistan in collaboration with the local health specialists, radiologists, and technologists. A comparison was made between the performance of the segmentation techniques used, and the model that performed the best in detecting tumors and normal breast regions was selected. The evaluation metrics, such as the mean IoU, pixel accuracy, and an in-depth experimental evaluation were used as performance parameters. This investigation determined how well semantic segmentation techniques were performed based on two datasets (cityscapes and mammograms) in this study. The global Dilation 10 semantic segmentation model outperformed the other three semantic segmentation models with a pixel accuracy of 92.98 percent in comparison tests. This paper demonstrates the efficacy of pixel-wise image segmentation techniques and their superiority to other techniques by outperforming other current state-of-the-art automatic image segmentation models. [ABSTRACT FROM AUTHOR]

Soil erosion and land degradation have intensified recently, resulting from large‐scale land‐use and land cover (LULC) change, deforestation and farm mechanization. This phenomenon motivates the rationale for the assessment of such land‐use changes and their impacts on soil and vegetation in the Kanshi River basin using various remote sensing techniques between 1987–2019. The image classification enabled the identification of dry and highland zones. It was observed that around 17% of natural vegetation cover disappeared and was converted into agricultural land. Significant increase in extensive agricultural practices, population growth, settlement, and the brick industry have increased soil erosion and changed the landscape of the Kanshi region during 1987–2019. Further, we classify gully erosion, rill erosion, sprinkle erosion, and sheet erosion have all been found at rates of 43%, 27%, 9%, and 21%, respectively. Similarly, soil classes in 2019 were doubled, with Sambrial association (1%), Rajar complex (36%), Dhulian association (15%), Gullied (15%), Missa complex, Rough mountainous (2%) and Rough broken (17%), compared to four classes in 1987: Gullied, Missa complex, rough broken land, and Torrent bed land. Whereas in 1987, four types of soils were observed. The recorded soil series had a limited water holding capacity and were well drained. Soil erosion is a natural and inevitable phenomenon; however, its intensity can be reduced by appropriate water resource management in this basin. [ABSTRACT FROM AUTHOR]

Land use/land cover (LULC) changes due to urban growth on the regional scale affect land surface temperature (LST). The present study aims to assess the LULC changes and their impact on LST over Mardan and Charsadda districts of Khyber Pakhtunkhwa (KP), Pakistan, in the period from 1990 to 2019. Landsat satellite (TM& ETM +) datasets in the period from 1990 to 2010 and Sentinel-2 images from 2016 to 2019 were used in this study. All the datasets were pre-processed and the LULC types were classified by maximum likelihood classification algorithm. The vegetation degradation was computed from normalized difference vegetation index (NDVI), and the LST was derived based on the LULC changes. The results showed that the overall accuracy of LULC classification was 87.84%. Dramatic LULC changes were observed during the last three decades, where the vegetation degradation area was decreased from 1307.8 (59.27%) to 1147.6 km2 (52.1%) and the barren land area increased from 816.6 (37.07%) to 961.4 km2 (42.64%). Similarly, the built-up area has also increased from 57.2 (2.5%) to 104.3 km2 (4.73%) in the years 1990 and 2019, respectively. These variations in LULC types have significantly influenced the LST from 1990 to 2019; specifically, the LST of built-up area, barren land, and vegetation cover increased from 20.1 to 32.1 °C, 21.5 to 35.5 °C, and 17.1 to 28.2 °C, respectively. The regression line plotted defines that the LST has a negative correlation with NDVI and a positive correlation with normalized difference of built-up index (NDBI). In particular, the vegetation and land covers dramatically transformed to barren land and/or to urban development over the study area in the period from 1990 to2019, which has severely affected the LST and the natural resources of the study area. Therefore, our study will be very helpful for managing the rapid environmental changes and urban planning. [ABSTRACT FROM AUTHOR]

Accurate and timely information about production estimates of wheat is useful for policymakers and government planners. The traditional methods for yield forecasting are labor insensitive and time-consuming therefore remote sensing is an effective approach for precise yield forecasting. The study was planned to develop a comprehensive framework for yield forecasting and to assess interannual yield variability in semi-arid regions. For wheat area classification, the peak season Landsat-8 satellite images were acquired, and Top of Atmospheric (TOA) correction was performed. The ground-truthing points of 100 farms were collected from the study area for the training of algorithms. The eight machine learning algorithms were used tune and tested using 10-k fold cross-validation and the best model was used for land cover classification of wheat. For yield forecasting, the temporal normalized difference vegetation index (NDVI) and land surface temperature (LST) were derived for the wheatgrowing season from November to April. A Principal Component Analysis (PCA) was used to variable selection and then Least Absolute Shrinkage Selection Operator (LASSO) analysis was performed to develop coefficients of the yield forecasting model. The developed model was further used in yield forecasting of 10 years (2008-2018) in four semi-arid regions. The predicted yield was compared with Crop Reporting Service (CRS), Pakistan department. The results of all machine learning algorithms showed an accuracy of 88% to 96%, however, the Random forest algorithm showed higher accuracy, which was further used for classification. The wheat estimated area of 6.9% was less than reported by CRS. For interannual variability, the relationship of observed (CRS) and predicted yield of 10 years showed a close relation with R2 ranged from 0.69 to 0.75 in the semi-arid region of Punjab, Pakistan. It was concluded that machine learning algorithms can be used as novel tools for yield forecasting and assessment of interannual yield variability. [ABSTRACT FROM AUTHOR]

Flood monitoring was conducted using multi-sensor data from space-borne optical, and microwave sensors; with cross-validation by ground-based rain gauges and stream flow stations along the Indus River; Pakistan. First; the optical imagery from the Moderate Resolution Imaging Spectroradiometer (MODIS) was processed to delineate the extent of the 2010 flood along Indus River; Pakistan. Moreover; the all-weather all-time capability of higher resolution imagery from the Advanced Synthetic Aperture Radar (ASAR) is used to monitor flooding in the lower Indus river basin. Then a proxy for river discharge from the Advanced Microwave Scanning Radiometer (AMSR-E) aboard NASA's Aqua satellite and rainfall estimates from the Tropical Rainfall Measuring Mission (TRMM) are used to study stream flow time series and precipitation patterns. The AMSR-E detected water surface signal was cross-validated with ground-based river discharge observations at multiple stream flow stations along the main Indus River. A high correlation was found; as indicated by a Pearson correlation coefficient of above 0.8 for the discharge gauge stations located in the southwest of Indus River basin. It is concluded that remote-sensing data integrated from multi spectral and microwave sensors could be used to supplement stream gauges in sparsely gauged large basins to monitor and detect floods. [ABSTRACT FROM AUTHOR]

The study of hand samples is a significant aspect of geoscience. This work showcases a technique for relatively quick and inexpensive mineral characterization, applied to a Cretaceous limestone formation and for sulfide-rich quartz vein samples from Northern Pakistan. Spectral feature parameters are derived from mineral mixtures of known abundance and are used for mineral mapping. Additionally, three well-known classification techniques—Spectral Angle Mapper (SAM), Support Vector Machine (SVM), and Neural Network—are compared. Point counting results from petrographic thin sections are used for validation the limestone samples, and QEMSCAN mineral maps for the sulfide samples. For classifying the carbonates, the SVM classifier produced results that are closest to the training set—with 84.4% accuracy and a kappa coefficient of 0.8. For classifying sulfides, SAM produced mineral abundances that were closest to the validation data, possibly due to the low reflectance of sulfides throughout the short-wave infrared spectrum with some differences in the overall spectral shape. [ABSTRACT FROM AUTHOR]