Retrieval of Case 2 Water Quality Parameters with Machine Learning

用于NASA EMIT和PACE任务的沿海水域浮游植物吸收系数与叶绿素a的高光谱反演变分自动编码器框架（Hyper-VAE）

Variational Autoencoder Framework for Hyperspectral Retrievals (Hyper-VAE) of Phytoplankton Absorption and Chlorophyll a in Coastal Waters for NASA's EMIT and PACE Missions

针对NASA EMIT和PACE任务，提出Hyper-VAE框架，首次定制变分自动编码器处理多分布预测问题，实现沿海水域浮游植物吸收系数与叶绿素a的高光谱反演，性能优于MDN，为水生生态研究提供新方法。

生成图像模型的不可检测水印

An Undetectable Watermark for Generative Image Models

提出首个不可检测的生成图像水印方案，利用伪随机纠错码选择扩散模型初始潜变量，保证质量不降且鲁棒，可编码512至2500位。

基于残差深度学习与新型机器学习水体分类的Sentinel 2全球叶绿素a反演算法

Global Chlorophyll-\textit{a} Retrieval algorithm from Sentinel 2 Using Residual Deep Learning and Novel Machine Learning Water Classification

本研究提出新型全球水体分类器GWC，结合XGBoost回归与残差CNN校正，构建Sentinel-2全球叶绿素a反演算法，实现无需额外调优的鲁棒可迁移反演性能。

A modeling system for monitoring the air - water pollution

Regular monitoring of key water quality parameters is important for assessing its the hydrological status in conjunction with air-pollution interaction. In this study, a new cost - effective technique based on the geo-ecological information-modeling system (GIMS) is implemented employing the combined use of simulation experiments and in field observations to investigate the problem of optimizing water quality monitoring. The GIMS, is accompanied by 39 elements selected in 8 management systems and 31 functional elements, which are described in detail. It is shown that the combined use of model …

基于物理的贝叶斯森林区SWE和积雪深度检索方法

Physically Informed Bayesian Retrieval of SWE and Snow Depth in Forested Areas from Airborne X And Ku-Band SAR Measurements

本研究提出了一种基于物理的贝叶斯方法，利用双频SAR观测数据在森林区实现SWE和积雪深度的高精度检索。

Analysis of the application of the optical method to the measurements of the water vapor content in the atmosphere - Part 1: Basic concepts of the measurement technique

We retrieved the total content of the atmospheric water vapor (or Integrated Water Vapor, IWV) from extensive sets of photometric data obtained since 1995 at Lindenberg Meteorological Observatory with star and sun photometers. Different methods of determination of the empirical parameters that are necessary for the retrieval are discussed. The instruments were independently calibrated using laboratory measurements made at Pulkovo Observatory with the VKM-100 multi-pass vacuum cell. The empirical parameters were also calculated by the simulation of the atmospheric absorption by water vapor, usi…