Search Results (2)

The continuous acquisition of spatial distribution information for offshore hydrocarbon exploitation (OHE) targets is crucial for the research of marine carbon emission activities. The methodological framework based on time-series night light remote sensing images with a feature increment strategy coupled with machine learning models has become one of the most novel techniques for OHE target extraction in recent years. Its performance is mainly influenced by machine learning models, target features, and regional differences. However, there is still a lack of internal comparative studies on the different influencing factors in this framework. Therefore, based on this framework, we selected four different typical experimental regions within the hydrocarbon basins in the South China Sea to validate the extraction performance of six machine learning models (the classification and regression tree (CART), random forest (RF), artificial neural networks (ANN), support vector machine (SVM), Mahalanobis distance (MaD), and maximum likelihood classification (MLC)) using time-series VIIRS night light remote sensing images. On this basis, the influence of the regional differences and the importance of the multi-features were evaluated and analyzed. The results showed that (1) the RF model performed the best, with an average accuracy of 90.74%, which was much higher than the ANN, CART, SVM, MLC, and MaD. (2) The OHE targets with a lower light radiant intensity as well as a closer spatial location were the main subjects of the omission extraction, while the incorrect extractions were mostly caused by the intensive ship activities. (3) The coefficient of variation was the most important feature that affected the accuracy of the OHE target extraction, with a contribution rate of 26%. This was different from the commonly believed frequency feature in the existing research. In the context of global warming, this study can provide a valuable information reference for studies on OHE target extraction, carbon emission activity monitoring, and carbon emission dynamic assessment. Full article

The South China Sea is rich in hydrocarbon resources and has been exploited for decades by countries around it. However, little is known about the hydrocarbon exploitation (HE) activities in the South China Sea in recent years, especially its intensity changes and development trends. Here, a long-time series of monthly Visible Infrared Imaging Radiometer Suite (VIIRS) nighttime light (NTL)images were applied to observe and analyze the HE dynamics in the South China Sea from 2012 to 2019. A target recognition method combining feature increment strategy and random forest model was proposed to obtain the spatial distribution of offshore HE targets, with an average comprehensive precision of 94.44%. Then, a spatio-temporal statistical analysis was carried out on the intensity changes and development trends of HE activities. The results showed that: (1) From 2012 to 2019, the quantity of HE targets in the South China Sea has increased from 215 to 310, from rapid to stable increasing taking 2014 as a turning point. (2) The distribution density of HE targets increases year by year, with the maximum density reaching 59/ 10,000 Km², and with the most significant increase in the new hydrocarbon-bearing fields close to the deep-sea. (3) The quantity of HE targets shallower than -300m has been increasing with years, but showing a decreasing proportion trend, falling from 96.7% in 2012 to 94.2% of the total in 2019. (4) After 2015, the exploitation core of most hydrocarbon-bearing basins began to shift from shallow-sea to deep-sea, with gradually increasing exploitation depth, among which the maximum depth reaching −1580 m. Against the background of the changes in international crude oil prices and the vigorous development of deep-sea HE, this research provides important information and methodological references for the formulation and analysis of offshore hydrocarbon resource exploitation strategies. Full article