Catalogue Search | MBRL
Are you sure you want to remove the book from the shelf?
{{itemTitle}}
1,954
result(s) for
"Geospatial data Data processing."
Sort by:
Deep Convolutional Neural Network for Flood Extent Mapping Using Unmanned Aerial Vehicles Data
Flooding is one of the leading threats of natural disasters to human life and property, especially in densely populated urban areas. Rapid and precise extraction of the flooded areas is key to supporting emergency-response planning and providing damage assessment in both spatial and temporal measurements. Unmanned Aerial Vehicles (UAV) technology has recently been recognized as an efficient photogrammetry data acquisition platform to quickly deliver high-resolution imagery because of its cost-effectiveness, ability to fly at lower altitudes, and ability to enter a hazardous area. Different image classification methods including SVM (Support Vector Machine) have been used for flood extent mapping. In recent years, there has been a significant improvement in remote sensing image classification using Convolutional Neural Networks (CNNs). CNNs have demonstrated excellent performance on various tasks including image classification, feature extraction, and segmentation. CNNs can learn features automatically from large datasets through the organization of multi-layers of neurons and have the ability to implement nonlinear decision functions. This study investigates the potential of CNN approaches to extract flooded areas from UAV imagery. A VGG-based fully convolutional network (FCN-16s) was used in this research. The model was fine-tuned and a k-fold cross-validation was applied to estimate the performance of the model on the new UAV imagery dataset. This approach allowed FCN-16s to be trained on the datasets that contained only one hundred training samples, and resulted in a highly accurate classification. Confusion matrix was calculated to estimate the accuracy of the proposed method. The image segmentation results obtained from FCN-16s were compared from the results obtained from FCN-8s, FCN-32s and SVMs. Experimental results showed that the FCNs could extract flooded areas precisely from UAV images compared to the traditional classifiers such as SVMs. The classification accuracy achieved by FCN-16s, FCN-8s, FCN-32s, and SVM for the water class was 97.52%, 97.8%, 94.20% and 89%, respectively.
Journal Article
Supporting Red List threat assessments with GeoCAT: geospatial conservation assessment tool
GeoCAT is an open source, browser based tool that performs rapid geospatial analysis to ease the process of Red Listing taxa. Developed to utilise spatially referenced primary occurrence data, the analysis focuses on two aspects of the geographic range of a taxon: the extent of occurrence (EOO) and the area of occupancy (AOO). These metrics form part of the IUCN Red List categories and criteria and have often proved challenging to obtain in an accurate, consistent and repeatable way. Within a familiar Google Maps environment, GeoCAT users can quickly and easily combine data from multiple sources such as GBIF, Flickr and Scratchpads as well as user generated occurrence data. Analysis is done with the click of a button and is visualised instantly, providing an indication of the Red List threat rating, subject to meeting the full requirements of the criteria. Outputs including the results, data and parameters used for analysis are stored in a GeoCAT file that can be easily reloaded or shared with collaborators. GeoCAT is a first step toward automating the data handling process of Red List assessing and provides a valuable hub from which further developments and enhancements can be spawned.
Journal Article
Geospatial assessment of climate variability and drought patterns: a case study from Pakistan
Drought substantially threatens Pakistan's agriculture, livestock, and environmental health, specifically in the Thal region. Climate change aggravates drought through extreme temperatures and unpredictable rainfall. This study aims to identify drought-prone districts in Bhakkar, Layyah, Khushab, and Muzaffargarh by correlating climatic parameters with drought vulnerability. Monthly precipitation data was sourced from CHRIPS, while district-level temperature data was obtained from the Climatic Research Unit (CRU) from 1981 to 2020. Vegetation data for six specific years (2001–02, 2004, 2006, and 2019–20) was analyzed using the MODIS product MO13Q1, which offers spatial and temporal resolutions of 250 m and 16 days, respectively. The highest drought severity was noted in 2001 and 2002, severely affecting Muzaffargarh, Layyah, Bhakkar, and Khushab. Moderate drought conditions were observed in 2004 and 2006, with slight improvements in Bhakkar and Layyah. Conversely, 2019 and 2020 saw low or no drought, marked by significant improvements in vegetative health due to increased rainfall. In 2001, higher monsoon temperatures were linked to increased rainfall, affecting STVI and NDVI values. In 2002, concentrated rainfall from July to September showed significant correlations with STVI (0.01) and NDVI (0.05), impacting early-year indices. During the moderate drought conditions of 2006, positive correlations emerged between rainfall and temperature, influencing STVI (0.01) and NDVI (0.05), while temperature correlated with DVI (0.05). In 2019–2020, high monsoon rainfall affected indices differently due to seasonal temperature variations. Pearson’s correlation analysis revealed significant relationships between rainfall and temperature with STVI (0.01) and NDVI (0.05), as well as between temperature and DVI (0.05). This study emphasizes the necessity for ongoing drought monitoring and adaptive management strategies in the Thal region to mitigate the impacts of climate variability on agriculture and vegetation health.
Journal Article
Preliminary Principles and Guidelines for Archiving Environmental and Geospatial Data at NOAA
The National Oceanic and Atmospheric Administration (NOAA) collects and manages a wide range of environmental and geospatial data to fulfill its mission requirements-data that stretch from the surface of the sun to the core of the earth, and affect every aspect of society. With limited resources and enormous growth in data volumes, NOAA asked the National Academies for advice on how to archive and provide access to these data. This book offers preliminary principles and guidelines that NOAA and its partners can use to begin planning specific archiving strategies for the data streams they currently collect. For example, the book concludes that the decision to archive environmental or geospatial data should be driven by its current or future value to society, and that funding for environmental and geospatial measurements should include sufficient resources to archive and provide access to the data these efforts generate. The preliminary principles and guidelines proposed in this book will be refined and expanded to cover data access issues in a final book expected to be released in 2007.
eBook
MRENet: Simultaneous Extraction of Road Surface and Road Centerline in Complex Urban Scenes from Very High-Resolution Images
Automatic extraction of the road surface and road centerline from very high-resolution (VHR) remote sensing images has always been a challenging task in the field of feature extraction. Most existing road datasets are based on data with simple and clear backgrounds under ideal conditions, such as images derived from Google Earth. Therefore, the studies on road surface extraction and road centerline extraction under complex scenes are insufficient. Meanwhile, most existing efforts addressed these two tasks separately, without considering the possible joint extraction of road surface and centerline. With the introduction of multitask convolutional neural network models, it is possible to carry out these two tasks simultaneously by facilitating information sharing within a multitask deep learning model. In this study, we first design a challenging dataset using remote sensing images from the GF-2 satellite. The dataset contains complex road scenes with manually annotated images. We then propose a two-task and end-to-end convolution neural network, termed Multitask Road-related Extraction Network (MRENet), for road surface extraction and road centerline extraction. We take features extracted from the road as the condition of centerline extraction, and the information transmission and parameter sharing between the two tasks compensate for the potential problem of insufficient road centerline samples. In the network design, we use atrous convolutions and a pyramid scene parsing pooling module (PSP pooling), aiming to expand the network receptive field, integrate multilevel features, and obtain more abundant information. In addition, we use a weighted binary cross-entropy function to alleviate the background imbalance problem. Experimental results show that the proposed algorithm outperforms several comparative methods in the aspects of classification precision and visual interpretation.
Journal Article