A new oil spill detection algorithm based on Dempster-Shafer evidence theory

Features of oil spills and look-alikes in polarimetric synthetic aperture radar(SAR)images always play an important role in oil spill detection.Many oil spill detection algorithms have been implemented based on these features.Although environmental factors such as wind speed are important to distinguish oil spills and look-alikes,some oil spill detection algorithms do not consider the environmental factors.To distinguish oil spills and look-alikes more accurately based on environmental factors and image features,a new oil spill detection algorithm based on Dempster-Shafer evidence theory was proposed.The process of oil spill detection taking account of environmental factors was modeled using the subjective Bayesian model.The Faster-region convolutional neural networks(RCNN)model was used for oil spill detection based on the convolution features.The detection results of the two models were fused at decision level using Dempster-Shafer evidence theory.The establishment and test of the proposed algorithm were completed based on our oil spill and look-alike sample database that contains 1798 image samples and environmental information records related to the image samples.The analysis and evaluation of the proposed algorithm shows a good ability to detect oil spills at a higher detection rate,with an identifi cation rate greater than 75%and a false alarm rate lower than 19%from experiments.A total of 12 oil spill SAR images were collected for the validation and evaluation of the proposed algorithm.The evaluation result shows that the proposed algorithm has a good performance on detecting oil spills with an overall detection rate greater than 70%.

Nitrogen cycle of a typical Suaeda salsa marsh ecosystem in the Yellow River estuary

The nitrogen（N） biological cycle of the Suaeda salsa marsh ecosystem in the Yellow River estuary was studied during 2008 to 2009.Results showed that soil N had significant seasonal fluctuations and vertical distribution.The N/P ratio（15.73±1.77） of S.salsa was less than 16,indicating that plant growth was limited by both N and P.The N absorption coefficient of S.salsa was very low（0.007）,while the N utilization and cycle coefficients were high（0.824 and 0.331,respectively）.The N turnover among compartments of S.salsa marsh showed that N uptake from aboveground parts and roots were 2.539 and 0.622 g/m2,respectively.The N translocation from aboveground parts to roots and from roots to soil were 2.042 and 0.076 g/m2,respectively.The N translocation from aboveground living bodies to litter was 0.497 g/m2,the annual N return from litter to soil was far less than 0.368 g/m2,and the net N mineralization in topsoil during the growing season was 0.033 g/m2.N was an important limiting factor in S.salsa marsh,and the ecosystem was classified as unstable and vulnerable.S.salsa was seemingly well adapted to the low-nutrient status and vulnerable habitat,and the nutrient enrichment due to N import from the Yellow River estuary would be a potential threat to the S.salsa marsh.Excessive nutrient loading might favor invasive species and induce severe long-term degradation of the ecosystem if human intervention measures were not taken.The N quantitative relationships determined in our study might provide a scientific basis for the establishment of effective measures.