Catalogue Search | MBRL
Are you sure you want to remove the book from the shelf?
{{itemTitle}}
356
result(s) for
"Atkinson, Peter M."
Sort by:
Deep learning-based landslide susceptibility mapping
Landslides are considered as one of the most devastating natural hazards in Iran, causing extensive damage and loss of life. Landslide susceptibility maps for landslide prone areas can be used to plan for and mitigate the consequences of catastrophic landsliding events. Here, we developed a deep convolutional neural network (CNN–DNN) for mapping landslide susceptibility, and evaluated it on the Isfahan province, Iran, which has not previously been assessed on such a scale. The proposed model was trained and validated using training (80%) and testing (20%) datasets, each containing relevant data on historical landslides, field records and remote sensing images, and a range of geomorphological, geological, environmental and human activity factors as covariates. The CNN–DNN model prediction accuracy was tested using a wide range of statistics from the confusion matrix and error indices from the receiver operating characteristic (ROC) curve. The CNN–DNN model was evaluated comprehensively by comparing it to several state-of-the-art benchmark machine learning techniques including the support vector machine (SVM), logistic regression (LR), Gaussian naïve Bayes (GNB), multilayer perceptron (MLP), Bernoulli Naïve Bayes (BNB) and decision tree (DT) classifiers. The CNN–DNN model for landslide susceptibility mapping was found to predict more accurately than the benchmark algorithms, with an AUC = 90.9%, IRs = 84.8%, MSE = 0.17, RMSE = 0.40, and MAPE = 0.42. The map provided by the CNN–DNN clearly revealed a high-susceptibility area in the west and southwest, related to the main Zagros trend in the province. These findings can be of great utility for landslide risk management and land use planning in the Isfahan province.
Journal Article
COVID-19 Outbreak Prediction with Machine Learning
Several outbreak prediction models for COVID-19 are being used by officials around the world to make informed decisions and enforce relevant control measures. Among the standard models for COVID-19 global pandemic prediction, simple epidemiological and statistical models have received more attention by authorities, and these models are popular in the media. Due to a high level of uncertainty and lack of essential data, standard models have shown low accuracy for long-term prediction. Although the literature includes several attempts to address this issue, the essential generalization and robustness abilities of existing models need to be improved. This paper presents a comparative analysis of machine learning and soft computing models to predict the COVID-19 outbreak as an alternative to susceptible–infected–recovered (SIR) and susceptible-exposed-infectious-removed (SEIR) models. Among a wide range of machine learning models investigated, two models showed promising results (i.e., multi-layered perceptron, MLP; and adaptive network-based fuzzy inference system, ANFIS). Based on the results reported here, and due to the highly complex nature of the COVID-19 outbreak and variation in its behavior across nations, this study suggests machine learning as an effective tool to model the outbreak. This paper provides an initial benchmarking to demonstrate the potential of machine learning for future research. This paper further suggests that a genuine novelty in outbreak prediction can be realized by integrating machine learning and SEIR models.
Journal Article
Three-Fold Urban Expansion in Saudi Arabia from 1992 to 2013 Observed Using Calibrated DMSP-OLS Night-Time Lights Imagery
Although Saudi Arabia has experienced very high rates of urbanization, little interest has been given to investigating national and provincial trends in urbanization in space and time. Night-time lights satellite sensor data are considered as a suitable source of imagery for mapping urban areas across large regions. This study uses night-time lights data to analyze the spatial and temporal patterns and dynamics of urban growth in Saudi Arabia between 1992 and 2013 at the national and provincial levels. A hybrid method was applied to ensure the continuity and consistency of the Defense Meteorological Satellite Program (DMSP) Operational Line-Scan System (OLS) of stable night-time (SNT) data through time. As a result of spatial variation in the character of urban areas across Saudi Arabia, different thresholds were used to derive urban areas from the imagery. The extracted urban morphology was assessed using socio-economic data and finer resolution imagery, and accuracy assessment revealed excellent agreement. Based on the rigorous stepwise calibration analysis undertaken here, urban areas in Saudi Arabia were found to have increased three-fold between 1992 and 2013, with most of the increase concentrated in three provinces (Makkah, Riyadh and Eastern). In addition, significant variation was observed in urbanization at the provincial level. The observed high rates of urban growth are aligned with the prosperity and socio-economic development of Saudi Arabia over the last 40 years. The research shows that DMSP-OLS SNT data can provide a valuable source of information for mapping the space–time dynamics of urban growth across very large areas. Such data are required by urban and regional planners, as well as policy makers, for characterizing urban growth patterns, interpreting the drivers of such dynamics and for forecasting future growth, as well as achieving sustainable development management.
Journal Article
Deep learning enables satellite-based monitoring of large populations of terrestrial mammals across heterogeneous landscape
New satellite remote sensing and machine learning techniques offer untapped possibilities to monitor global biodiversity with unprecedented speed and precision. These efficiencies promise to reveal novel ecological insights at spatial scales which are germane to the management of populations and entire ecosystems. Here, we present a robust transferable deep learning pipeline to automatically locate and count large herds of migratory ungulates (wildebeest and zebra) in the Serengeti-Mara ecosystem using fine-resolution (38-50 cm) satellite imagery. The results achieve accurate detection of nearly 500,000 individuals across thousands of square kilometers and multiple habitat types, with an overall F1-score of 84.75% (Precision: 87.85%, Recall: 81.86%). This research demonstrates the capability of satellite remote sensing and machine learning techniques to automatically and accurately count very large populations of terrestrial mammals across a highly heterogeneous landscape. We also discuss the potential for satellite-derived species detections to advance basic understanding of animal behavior and ecology.
This study presents a deep learning pipeline to automatically locate and count large herds of migratory ungulates (wildebeest and zebra) in the Serengeti-Mara ecosystem using fine resolution satellite imagery. The results achieve accurate detection of nearly 500,000 individuals across thousands of square kilometers and multiple habitat types.
Journal Article
Dramatic Loss of Agricultural Land Due to Urban Expansion Threatens Food Security in the Nile Delta, Egypt
Egypt has one of the largest and fastest growing populations in the world. However, nearly 96% of the total land area is uninhabited desert and 96% of the population is concentrated around the River Nile valley and the Delta. This unbalanced distribution and dramatically rising population have caused severe socio-economic problems. In this research, 24 land use/land cover (LULC) maps from 1992 to 2015 were used to monitor LULC changes in the Nile Delta and quantify the rates and types of LULC transitions. The results show that 74,600 hectares of fertile agricultural land in the Nile Delta (Old Lands) was lost to urban expansion over the 24 year period at an average rate of 3108 ha year−1, whilst 206,100 hectares of bare land was converted to agricultural land (New Lands) at an average rate of 8588 ha year−1. A Cellular Automata-Markov (CA-Markov) integrated model was used to simulate future alternative LULC change scenarios. Under a Business as Usual scenario, 87,000 hectares of land transitioned from agricultural land to urban areas by 2030, posing a threat to the agricultural sector sustainability and food security in Egypt. Three alternative future scenarios were developed to promote urban development elsewhere, hence, with potential to preserve the fertile soils of the Nile Delta. A scenario which permitted urban expansion into the desert only preserved the largest amount of agricultural land in the Nile Delta. However, a scenario that encouraged urban expansion into the desert and adjacent to areas of existing high population density resulted in almost the same area of agricultural land being preserved. The alternative future scenarios are valuable for supporting policy development and planning decisions in Egypt and demonstrating that continued urban development is possible while minimising the threats to environmental sustainability and national food security.
Journal Article
Global land cover trajectories and transitions
Global land cover (LC) changes threaten sustainability and yet we lack a comprehensive understanding of the gains and losses of LC types, including the magnitudes, locations and timings of transitions. We used a novel, fine-resolution and temporally consistent satellite-derived dataset covering the entire Earth annually from 1992 to 2018 to quantify LC changes across a range of scales. At global and continental scales, the observed trajectories of change for most LC types were fairly smooth and consistent in direction through time. We show these observed trajectories in the context of error margins produced by extrapolating previously published accuracy metrics associated with the LC dataset. For many LC classes the observed changes were found to be within the error margins. However, an important exception was the increase in urban land, which was consistently larger than the error margins, and for which the LC transition was unidirectional. An advantage of analysing the global, fine spatial resolution LC time-series dataset is the ability to identify where and when LC changes have taken place on the Earth. We present LC change maps and trajectories that identify locations with high dynamism, and which pose significant sustainability challenges. We focused on forest loss and urban growth at the national scale, identifying the top 10 countries with the largest percentages of forest loss and urban growth globally. Crucially, we found that most of these ‘worst-case’ countries have stabilized their forest losses, although urban expansion was monotonic in all cases. These findings provide crucial information to support progress towards the UN’s SDGs.
Journal Article
Impacts of environmental and socio-economic factors on emergence and epidemic potential of Ebola in Africa
Recent outbreaks of animal-borne emerging infectious diseases have likely been precipitated by a complex interplay of changing ecological, epidemiological and socio-economic factors. Here, we develop modelling methods that capture elements of each of these factors, to predict the risk of Ebola virus disease (EVD) across time and space. Our modelling results match previously-observed outbreak patterns with high accuracy, and suggest further outbreaks could occur across most of West and Central Africa. Trends in the underlying drivers of EVD risk suggest a 1.75 to 3.2-fold increase in the endemic rate of animal-human viral spill-overs in Africa by 2070, given current modes of healthcare intervention. Future global change scenarios with higher human population growth and lower rates of socio-economic development yield a 1.63-fold higher likelihood of epidemics occurring as a result of spill-over events. Our modelling framework can be used to target interventions designed to reduce epidemic risk for many zoonotic diseases.
The capacity to predict zoonotic disease outbreaks is hampered by data availability and complex relationships between humans, wildlife, and the environment. Here the authors present a modelling framework that identifies potential high-risk locations for Ebola outbreaks under various climatic, demographic, and land use scenarios.
Journal Article
Spatiotemporal Variation in Surface Urban Heat Island Intensity and Associated Determinants across Major Chinese Cities
Urban heat islands (UHIs) created through urbanization can have negative impacts on the lives of people living in cities. They may also vary spatially and temporally over a city. There is, thus, a need for greater understanding of these patterns and their causes. While previous UHI studies focused on only a few cities and/or several explanatory variables, this research provides a comprehensive and comparative characterization of the diurnal and seasonal variation in surface UHI intensities (SUHIIs) across 67 major Chinese cities. The factors associated with the SUHII were assessed by considering a variety of related social, economic and natural factors using a regression tree model. Obvious seasonal variation was observed for the daytime SUHII, and the diurnal variation in SUHII varied seasonally across China. Interestingly, the SUHII varied significantly in character between northern and southern China. Southern China experienced more intense daytime SUHIIs, while the opposite was true for nighttime SUHIIs. Vegetation had the greatest effect in the day time in northern China. In southern China, annual electricity consumption and the number of public buses were found to be important. These results have important theoretical significance and may be of use to mitigate UHI effects.
Journal Article
Forecasting of Built-Up Land Expansion in a Desert Urban Environment
In recent years, socioeconomic transformation and social modernisation in the Gulf Cooperation Council (GCC) states have led to tremendous changes in lifestyle and, subsequently, expansion of urban settlements. This accelerated growth is pronounced not only across vegetated coasts, plains, and mountains, but also in desert cities. Nevertheless, spatial simulation and prediction of desert urban patterns has received little attention, including in Oman. While most urban settlements in Oman are located in desert environments, research exploring and monitoring this type of urban growth is rare in the scientific literature. This research focuses on analysing and predicting land use–land cover (LULC) changes across the desert city of Ibri in Oman. A methodology was employed involving integrating the multilayer perceptron (MLP) and Markov chain (MC) techniques to forecast spatiotemporal LULC dynamics and map urban growth patterns. The inputs were three Landsat images from 2010 and 2020, and a series of covariate layers based on transforms of elevation, slope, population settlements, urban centres, and points of interest that proxy the driving forces of change. The findings indicated that the observed LULC changes were predominantly rapid across the city during 2010 to 2020, transforming desert, bare land, and vegetation into built-up areas. The forecast showed that area of land conversion from desert to urban would be 5666 ha during the next two decades and 7751 ha by 2050. Similarly, vacant land is expected to contribute large areas to urban expansion (2370 ha by 2040, and 3266 ha by 2050), although desert cities confront numerous environmental challenges, including water scarcity, shrinking vegetation cover, and being converted into residential land. Massive urban expansion has consequences for biodiversity and natural ecosystems—particularly in green areas, which are expected to decline by approximately 107 ha by 2040 (i.e., 10%) and 166 ha by 2050. The outcomes of this research provide fundamental guidance for decision-makers and planners in Oman and elsewhere to effectively monitor and manage desert urban dynamics and sustainable desert cities.
Journal Article