首页|New Machine Learning Study Findings Reported from Chinese Academy of Sciences [High-resolution ocean color reconstruction and analysis focusing on Kd490 via ma chine learning model integration of MODIS and Sentinel-2 (MSI)]
New Machine Learning Study Findings Reported from Chinese Academy of Sciences [High-resolution ocean color reconstruction and analysis focusing on Kd490 via ma chine learning model integration of MODIS and Sentinel-2 (MSI)]
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Investigators discuss new findings in artificial intelligence. According to news reporting out of Shanghai, People's R epublic of China, by NewsRx editors, research stated, "Oceanic water quality mon itoring is essential for environmental protection, resource management, and ecos ystem vitality. Optical remote sensing from space plays a pivotal role in global surveillance of oceanic water quality." Funders for this research include National Natural Science Foundation of China; Youth Innovation Promotion Association of The Chinese Academy of Sciences; Shang hai Rising-star Program. Our news journalists obtained a quote from the research from Chinese Academy of Sciences: "However, the spatial resolution of current ocean color data products falls short of scrutinizing intricate small-scale marine features. This study in troduces a hybrid model that fuses MODIS (Moderate Resolution lmaging Spectrorad iometer) ocean color products with Sentinel-2 ‘s remote sensing reflectance data to generate high-resolution ocean color imagery, specifically investigating the diffuse attenuation coefficient at a wavelength of 490 nm (Kd490). To address t he intricacies of coastal environments, we propose two complementary strategies to improve the accuracy of inversion. The first strategy leverages MODIS ocean c olor products alongside a geographic segmentation model to perform distinct inve rsions for separate marine zones, enhancing spatial resolution and specificity i n coastal regions. The second strategy bolsters model interpretability during tr aining by integrating predictions from conventional physical models into a Rando m Forest-based Regression Ensemble (RFRE) model. This study focuses on the coast al regions surrounding the Beibu Gulf, near Hainan Island in China. Our findings exhibit a strong concordance with MODIS products, achieving a monthly average c oefficient of determination (R²) of 0.90, peaking at 0.97, and sustaining a mont hly average root-mean-square error (RMSE) of less than 0.02."
Chinese Academy of SciencesShanghaiP eople's Republic of ChinaAsiaCyborgsEmerging TechnologiesMachine Learnin gRemote Sensing
NETL
NSTL
