Accurate PM2.5 concentration prediction is crucial for protecting public health and improving air quality. As a popular deep learning model, deep belief network (DBN) for PM2.5 concentration prediction has received increasing attention due to its effectiveness. However, the DBN structure parameters that have a significant impact on prediction accuracy and computation time are hard to be determined. To address this issue, a modified grey wolf optimization (MGWO) algorithm is proposed to optimize the DBN structure parameters containing number of hidden nodes, learning rate, and momentum coefficient. The methodology modifies the basic grey wolf optimization (GWO) algorithm using the nonlinear convergence and position update strategies, and then utilizes the training error of the DBN to calculate the fitness function of the MGWO algorithm. Through the multiple iterations, the optimal structure parameters are obtained, and a suitable predictor is finally generated. The proposed prediction model is validated on a real application case. Compared with the other prediction models, experimental results show that the proposed model has a simpler structure but higher prediction accuracy.

Oil spill incidents threaten the marine ecological environment. Detecting sea surface oil slicks by remote sensing images provides support for the efficient treatment of oil spills. This is important for sustainable marine development. However, traditional methods based on field analysis are time-consuming. Spectral indices lack applicability. In addition, traditional machine learning methods strictly rely on training and testing samples which are in short supply in oil spill images. Inspired by the spectral DNA encoding method, a spectral gene extraction (SGE) method was proposed to detect oil spills in hyperspectral images (HSI) and multispectral images (MSI). The SGE method contained a parameter and two strategies. The parameter of elimination was designed based on the population genetic frequency. It was used to control the number of spectral genes. The spectral gene extraction strategies, named largest in-class similarity (LIS) strategy and largest inter-class difference (LID) strategy, were proposed to mine the spectral genes by oil spill samples. The oil spills would be determined by calculating the similarity of the extracted spectral genes to the DNA encoded images. In this research, the SGE method was validated by two AVIRIS images of the Gulf of Mexico oil spill, one MODIS image of the Gulf of Mexico oil spill, and one Landsat 8 image of a Persian Gulf oil spill. The oil spills in different remote sensing images could be detected accurately by the proposed method in a small set of samples. Experimental results indicated that the proposed method was suitable for detecting marine oil spills in AVIRIS, MODIS, and Landsat 8 images. In addition, the SGE method with the LIS strategy was more suitable for detecting oil spills in HSI. Its proper elimination rates were 0.8~1.0. The SGE method with the LID strategy was more suitable for detecting oil spills in MSI. Its proper elimination rates were 0.5~0.7.

Remote sensing technologies are suitable for detecting marine oil-gas leakages on a large scale. It is important to structure an accurate method for detecting marine oil-gas leakages in varied remote sensing images. However, traditional spectral indexes have limited applicability. Machine learning methods need plenty of training and testing samples to establish the optimized models, which is too rigorous for satellite images. Thus, we proposed a multi-scale encoding (MSE) method with spectral shape information (SSI) to detect the oil-gas leakages in multi-source remote sensing data. First, the spectral amplitude information (SAI) and SSI of the original spectra were encoded into a series of code words according to the scales. Then, the differential code words of the marine oil-gas leakage objects were extracted from the SAI and SSI code words. Finally, the pixels of the encoded hyperspectral image (HSI) and multispectral image (MSI) would be determined by the differential code words. Seven images captured by different platforms/sensors (Landsat 7, Landsat 8, MODIS, Sentinel 2, Zhuhai-1, and AVIRIS) were used to validate the performance of the proposed method. The experimental results indicated that the MSE method with SSI was convergent and could detect the oil-gas leakages accurately in different images using a small set of samples.