scholarly journals Incorporating Automatic Satellite Detections of Oil Spills with Numerical Fate and Trajectory Modeling

2021 ◽  
Vol 2021 (1) ◽  
Author(s):  
Gabrielle G. McGrath ◽  
Tony Woolridge ◽  
Kelley Dodge ◽  
Masoud Mahdianpari
Keyword(s):  
Machine Learning ◽  
Numerical Modeling ◽  
Image Segmentation ◽  
Satellite Imagery ◽  
Newfoundland And Labrador ◽  
Oil Spills ◽  
Satellite Monitoring ◽  
False Alarms ◽  
Effective Response ◽  
Incident Investigation

ABSTRACT In recent years, access to freely available and commercial satellite imagery, such as Sentinel-1, RADARSAT-2, COSMO-SkyMed, and TerrsSAR-X, increased to the level where most global waters are observed at least once per day by one of these satellite platforms. The availability of this data combined with technological advancements in machine-learning and smart image segmentation allows for the potential to automatically detect oil spills and reduce the likelihood of false alarms. This improved satellite monitoring could result in early discovery of releases and the ability to launch a quicker response to mitigate potential damages. Numerical modeling will be used in combination with the detection results to determine the fate and trajectory of the oil as well as to hindcast where the oil was released. Implementing models into the process facilitates an effective response and incident investigation by determining where the oil is spreading and discovering where the oil originated. In 2019, Petroleum Research Newfoundland and Labrador (PRNL) launched a project led by C-CORE and RPS titled SpillSight to conduct a study into this technology for automatically detecting spills by satellite and modelling the outputs.

scholarly journals Machine Learning Methods Applied to the Prediction of Pseudo-nitzschia spp. Blooms in the Galician Rias Baixas (NW Spain)

2021 ◽  
Vol 10 (4) ◽  
pp. 199
Author(s):  
Francisco M. Bellas Aláez ◽  
Jesus M. Torres Palenzuela ◽  
Evangelos Spyrakos ◽  
Luis González Vilas
Keyword(s):  
Machine Learning ◽  
Performance Metrics ◽  
Prediction Models ◽  
Support Vector ◽  
False Alarms ◽  
Learning Approaches ◽  
Learning Methods ◽  
Machine Learning Methods ◽  
Rías Baixas ◽  
New Algorithms

This work presents new prediction models based on recent developments in machine learning methods, such as Random Forest (RF) and AdaBoost, and compares them with more classical approaches, i.e., support vector machines (SVMs) and neural networks (NNs). The models predict Pseudo-nitzschia spp. blooms in the Galician Rias Baixas. This work builds on a previous study by the authors (doi.org/10.1016/j.pocean.2014.03.003) but uses an extended database (from 2002 to 2012) and new algorithms. Our results show that RF and AdaBoost provide better prediction results compared to SVMs and NNs, as they show improved performance metrics and a better balance between sensitivity and specificity. Classical machine learning approaches show higher sensitivities, but at a cost of lower specificity and higher percentages of false alarms (lower precision). These results seem to indicate a greater adaptation of new algorithms (RF and AdaBoost) to unbalanced datasets. Our models could be operationally implemented to establish a short-term prediction system.

scholarly journals Identifying Urban Poverty Using High-Resolution Satellite Imagery and Machine Learning Approaches: Implications for Housing Inequality

Land ◽  
2021 ◽  
Vol 10 (6) ◽  
pp. 648
Author(s):  
Guie Li ◽  
Zhongliang Cai ◽  
Yun Qian ◽  
Fei Chen
Keyword(s):  
Machine Learning ◽  
High Resolution ◽  
Satellite Imagery ◽  
Low Income ◽  
Urban Poverty ◽  
Image Features ◽  
Housing Affordability ◽  
Learning Approaches ◽  
Housing Inequality ◽  
High Resolution Satellite Imagery

Enriching Asian perspectives on the rapid identification of urban poverty and its implications for housing inequality, this paper contributes empirical evidence about the utility of image features derived from high-resolution satellite imagery and machine learning approaches for identifying urban poverty in China at the community level. For the case of the Jiangxia District and Huangpi District of Wuhan, image features, including perimeter, line segment detector (LSD), Hough transform, gray-level cooccurrence matrix (GLCM), histogram of oriented gradients (HoG), and local binary patterns (LBP), are calculated, and four machine learning approaches and 25 variables are applied to identify urban poverty and relatively important variables. The results show that image features and machine learning approaches can be used to identify urban poverty with the best model performance with a coefficient of determination, R2, of 0.5341 and 0.5324 for Jiangxia and Huangpi, respectively, although some differences exist among the approaches and study areas. The importance of each variable differs for each approach and study area; however, the relatively important variables are similar. In particular, four variables achieved relatively satisfactory prediction results for all models and presented obvious differences in varying communities with different poverty levels. Housing inequality within low-income neighborhoods, which is a response to gaps in wealth, income, and housing affordability among social groups, is an important manifestation of urban poverty. Policy makers can implement these findings to rapidly identify urban poverty, and the findings have potential applications for addressing housing inequality and proving the rationality of urban planning for building a sustainable society.

scholarly journals Unraveling the deep learning gearbox in optical coherence tomography image segmentation towards explainable artificial intelligence

2021 ◽  
Vol 4 (1) ◽  
Author(s):  
Peter M. Maloca ◽  
Philipp L. Müller ◽  
Aaron Y. Lee ◽  
Adnan Tufail ◽  
Konstantinos Balaskas ◽  
...  
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Optical Coherence Tomography ◽  
Image Segmentation ◽  
Convolutional Neural Network ◽  
Learning Algorithm ◽  
Ground Truth ◽  
Optical Coherence Tomography Image ◽  
Optical Coherence ◽  
Tomography Image

AbstractMachine learning has greatly facilitated the analysis of medical data, while the internal operations usually remain intransparent. To better comprehend these opaque procedures, a convolutional neural network for optical coherence tomography image segmentation was enhanced with a Traceable Relevance Explainability (T-REX) technique. The proposed application was based on three components: ground truth generation by multiple graders, calculation of Hamming distances among graders and the machine learning algorithm, as well as a smart data visualization (‘neural recording’). An overall average variability of 1.75% between the human graders and the algorithm was found, slightly minor to 2.02% among human graders. The ambiguity in ground truth had noteworthy impact on machine learning results, which could be visualized. The convolutional neural network balanced between graders and allowed for modifiable predictions dependent on the compartment. Using the proposed T-REX setup, machine learning processes could be rendered more transparent and understandable, possibly leading to optimized applications.

scholarly journals Land Use Land Cover map segmentation using Remote Sensing: A Case study of Ajoy river watershed, India

2020 ◽  
Vol 30 (1) ◽  
pp. 273-286
Author(s):  
Kalyan Mahata ◽  
Rajib Das ◽  
Subhasish Das ◽  
Anasua Sarkar
Keyword(s):  
Land Use ◽  
Image Segmentation ◽  
Cellular Automata ◽  
Land Cover ◽  
Satellite Imagery ◽  
Current Model ◽  
Discrete Dynamical System ◽  
Land Use Land Cover ◽  
Data Set ◽  
Validity Indices

Abstract Image segmentation in land cover regions which are overlapping in satellite imagery, is one crucial challenge. To detect true belonging of one pixel becomes a challenging problem while classifying mixed pixels in overlapping regions. In current work, we propose one new approach for image segmentation using a hybrid algorithm of K-Means and Cellular Automata algorithms. This newly implemented unsupervised model can detect cluster groups using hybrid 2-Dimensional Cellular-Automata model based on K-Means segmentation approach. This approach detects different land use land cover areas in satellite imagery by existing K-Means algorithm. Since it is a discrete dynamical system, cellular automaton realizes uniform interconnecting cells containing states. In the second stage of current model, we experiment with a 2-dimensional cellular automata to rank allocations of pixels among different land-cover regions. The method is experimented on the watershed area of Ajoy river (India) and Salinas (California) data set with true class labels using two internal and four external validity indices. The segmented areas are then compared with existing FCM, DBSCAN and K-Means methods and verified with the ground truth. The statistical analysis results also show the superiority of the new method.

scholarly journals Using machine learning to automate image segmentation for analysis of in vitro osteoclast formation and bone resorption

Bone Reports ◽  
2021 ◽  
Vol 14 ◽  
pp. 100865
Author(s):  
B.K. Davies ◽  
Andrew Hibbert ◽  
Mark Hopkinson ◽  
Gill Holdsworth ◽  
Isabel Orriss
Keyword(s):  
Machine Learning ◽  
Image Segmentation ◽  
Bone Resorption ◽  
Osteoclast Formation

scholarly journals A Semi-Automated Object-Based Gully Networks Detection Using Different Machine Learning Models: A Case Study of Bowen Catchment, Queensland, Australia

Sensors ◽  
2019 ◽  
Vol 19 (22) ◽  
pp. 4893 ◽  
Author(s):  
Hejar Shahabi ◽  
Ben Jarihani ◽  
Sepideh Tavakkoli Piralilou ◽  
David Chittleborough ◽  
Mohammadtaghi Avand ◽  
...  
Keyword(s):  
Machine Learning ◽  
Image Segmentation ◽  
Vegetation Index ◽  
Scale Parameter ◽  
Slope Aspect ◽  
Support Vector ◽  
Topographic Wetness Index ◽  
Slope Length ◽  
Optimal Scale ◽  
Object Based

Gully erosion is a dominant source of sediment and particulates to the Great Barrier Reef (GBR) World Heritage area. We selected the Bowen catchment, a tributary of the Burdekin Basin, as our area of study; the region is associated with a high density of gully networks. We aimed to use a semi-automated object-based gully networks detection process using a combination of multi-source and multi-scale remote sensing and ground-based data. An advanced approach was employed by integrating geographic object-based image analysis (GEOBIA) with current machine learning (ML) models. These included artificial neural networks (ANN), support vector machines (SVM), and random forests (RF), and an ensemble ML model of stacking to deal with the spatial scaling problem in gully networks detection. Spectral indices such as the normalized difference vegetation index (NDVI) and topographic conditioning factors, such as elevation, slope, aspect, topographic wetness index (TWI), slope length (SL), and curvature, were generated from Sentinel 2A images and the ALOS 12-m digital elevation model (DEM), respectively. For image segmentation, the ESP2 tool was used to obtain three optimal scale factors. On using object pureness index (OPI), object matching index (OMI), and object fitness index (OFI), the accuracy of each scale in image segmentation was evaluated. The scale parameter of 45 with OFI of 0.94, which is a combination of OPI and OMI indices, proved to be the optimal scale parameter for image segmentation. Furthermore, segmented objects based on scale 45 were overlaid with 70% and 30% of a prepared gully inventory map to select the ML models’ training and testing objects, respectively. The quantitative accuracy assessment methods of Precision, Recall, and an F1 measure were used to evaluate the model’s performance. Integration of GEOBIA with the stacking model using a scale of 45 resulted in the highest accuracy in detection of gully networks with an F1 measure value of 0.89. Here, we conclude that the adoption of optimal scale object definition in the GEOBIA and application of the ensemble stacking of ML models resulted in higher accuracy in the detection of gully networks.

scholarly journals Satellite Monitoring Systems for Shipping and Offshore Oil and Gas Industry in the Baltic Sea

2015 ◽  
Vol 16 (2) ◽  
pp. 117-126 ◽  
Author(s):  
A.G. Kostianoy ◽  
E.V. Bulycheva ◽  
A.V. Semenov ◽  
A. Krainyukov
Keyword(s):  
Numerical Modeling ◽  
Baltic Sea ◽  
Oil And Gas ◽  
Oil Pollution ◽  
Oil Production ◽  
Satellite Monitoring ◽  
Monitoring Systems ◽  
Offshore Oil And Gas ◽  
The Baltic ◽  
Oil Rig

Abstract Shipping activities, oil production and transport in the sea, oil handled in harbors, construction and exploitation of offshore oil and gas pipelines have a number of negative impacts on the marine environment and coastal zone of the seas. In 2004-2014 we elaborated several operational satellite monitoring systems for oil and gas companies in Russia and performed integrated satellite monitoring of the ecological state of coastal waters in the Baltic, Black, Caspian, and Kara seas, which included observation of oil pollution, suspended matter, and algae bloom at a fully operational mode. These monitoring systems differ from the existing ones by the analysis of a wide spectrum of satellite, meteorological and oceanographic data, as well as by a numerical modeling of oil spill transformation and transport in real weather conditions. Our experience in the Baltic Sea includes: (1) integrated satellite monitoring of oil production at the LUKOIL-KMN Ltd. D-6 oil rig in the Southeastern Baltic Sea (Kravtsovskoe oil field) in 2004-2014; (2) integrated satellite monitoring of the “Nord Stream” underwater gas pipeline construction and exploitation in the Gulf of Finland (2010-2013); (3) numerical modeling of risks of oil pollution caused by shipping along the main maritime shipping routes in the Gulf of Finland, the Baltic Proper, and in the Southeastern Baltic Sea; (4) numerical modeling of risks of oil pollution caused by oil production at D-6 oil rig and oil transportation on shore via the connecting underwater oil pipeline.

Beyond Cloud: A Fused Optic and SAR Based Solution to Monitor Crop Health

2021 ◽  
Author(s):  
Brianna Pagán ◽  
Adekunle Ajayi ◽  
Mamadou Krouma ◽  
Jyotsna Budideti ◽  
Omar Tafsi
Keyword(s):  
Machine Learning ◽  
Satellite Imagery ◽  
Cloud Cover ◽  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
Learning Approaches ◽  
Area Index ◽  
Spatial And Temporal Scales ◽  
Field Level ◽  
Crop Health

<p>The value of satellite imagery to monitor crop health in near-real time continues to exponentially grow as more missions are launched making data available at higher spatial and temporal scales. Yet cloud cover remains an issue for utilizing vegetation indexes (VIs) solely based on optic imagery, especially in certain regions and climates. Previous research has proven the ability to reconstruct VIs like the Normalized Difference Vegetation Index (NDVI) and Leaf Area Index (LAI) by leveraging synthetic aperture radar (SAR) datasets, which are not inhibited by cloud cover. Publicly available data from SAR missions like Sentinel-1 at relatively decent spatial resolutions present the opportunity for more affordable options for agriculture users to integrate satellite imagery in their day to day operations. Previous research has successfully reconstructed optic VIs (i.e. from Sentinel-2) with SAR data (i.e. from Sentinel-1) leveraging various machine learning approaches for a limited number of crop types. However, these efforts normally train on individual pixels rather than leveraging information at a field level. </p><p>Here we present Beyond Cloud, a product which is the first to leverage computer vision and machine learning approaches in order to provide fused optic and SAR based crop health information. Field level learning is especially well-suited for inherently noisy SAR datasets. Several use cases are presented over agriculture fields located throughout the United Kingdom, France and Belgium, where cloud cover limits optic based solutions to as little as 2-3 images per growing season. Preliminary efforts for additional features to the product including automated crop and soil type detection are also discussed. Beyond Cloud can be accessed via a simple API which makes integration of the results easy for existing dashboards and smart-ag tools. Overall, these efforts promote the accessibility of satellite imagery for real agriculture end users.</p><p> </p>

Machine-Learning for the Prediction of Lost Circulation Events - Time Series Analysis and Model Evaluation

2021 ◽  
Author(s):  
Arturo Magana-Mora ◽  
Mohammad AlJubran ◽  
Jothibasu Ramasamy ◽  
Mohammed AlBassam ◽  
Chinthaka Gooneratne ◽  
...  
Keyword(s):  
Machine Learning ◽  
Time Series ◽  
Real Time ◽  
Large Scale ◽  
Model Comparison ◽  
Drilling Fluid ◽  
Sensor Data ◽  
False Alarms ◽  
Suitable Model ◽  
Lost Circulation

Abstract Objective/Scope. Lost circulation events (LCEs) are among the top causes for drilling nonproductive time (NPT). The presence of natural fractures and vugular formations causes loss of drilling fluid circulation. Drilling depleted zones with incorrect mud weights can also lead to drilling induced losses. LCEs can also develop into additional drilling hazards, such as stuck pipe incidents, kicks, and blowouts. An LCE is traditionally diagnosed only when there is a reduction in mud volume in mud pits in the case of moderate losses or reduction of mud column in the annulus in total losses. Using machine learning (ML) for predicting the presence of a loss zone and the estimation of fracture parameters ahead is very beneficial as it can immediately alert the drilling crew in order for them to take the required actions to mitigate or cure LCEs. Methods, Procedures, Process. Although different computational methods have been proposed for the prediction of LCEs, there is a need to further improve the models and reduce the number of false alarms. Robust and generalizable ML models require a sufficiently large amount of data that captures the different parameters and scenarios representing an LCE. For this, we derived a framework that automatically searches through historical data, locates LCEs, and extracts the surface drilling and rheology parameters surrounding such events. Results, Observations, and Conclusions. We derived different ML models utilizing various algorithms and evaluated them using the data-split technique at the level of wells to find the most suitable model for the prediction of an LCE. From the model comparison, random forest classifier achieved the best results and successfully predicted LCEs before they occurred. The developed LCE model is designed to be implemented in the real-time drilling portal as an aid to the drilling engineers and the rig crew to minimize or avoid NPT. Novel/Additive Information. The main contribution of this study is the analysis of real-time surface drilling parameters and sensor data to predict an LCE from a statistically representative number of wells. The large-scale analysis of several wells that appropriately describe the different conditions before an LCE is critical for avoiding model undertraining or lack of model generalization. Finally, we formulated the prediction of LCEs as a time-series problem and considered parameter trends to accurately determine the early signs of LCEs.

Using Machine Learning Models to Detect Oil Spills

2020 ◽  
Author(s):  
Ana Cláudia Souza Vidal de Negreiros ◽  
Caio Bezerra Souto Maior ◽  
Isis Didier Lins ◽  
Paulo Renato Soares ◽  
Márcio das Chagas Moura
Keyword(s):  
Machine Learning ◽  
Oil Spills ◽  
Learning Models ◽  
Machine Learning Models
Sign in / Sign up

Export Citation Format

Share Document