Author
Sensen Wu
Other affiliations: The Chinese University of Hong Kong
Bio: Sensen Wu is an academic researcher from Zhejiang University. The author has contributed to research in topics: Computer science & Environmental science. The author has an hindex of 6, co-authored 12 publications receiving 83 citations. Previous affiliations of Sensen Wu include The Chinese University of Hong Kong.
Papers
More filters
TL;DR: A geographically neural network weighted regression model that combines ordinary least squares (OLS) and neural networks to estimate spatial non-stationarity based on a concept similar to GWR is proposed and achieved better fitting accuracy and more adequate prediction than OLS and GWR.
Abstract: Geographically weighted regression (GWR) is a classic and widely used approach to model spatial non-stationarity. However, the approach makes no precise expressions of its weighting kernels and is ...
41 citations
TL;DR: To address complex non-linear interactions between time and space, a spatiotemporal proximity neural network (STPNN) is proposed in this paper to accurately generate space-time distance and has the potential to handle complex spatiotmporal non-stationarity in various geographical processes and environmental phenomena.
Abstract: Geographically weighted regression (GWR) and geographically and temporally weighted regression (GTWR) are classic methods for estimating non-stationary relationships. Although these methods have be...
30 citations
TL;DR: Wang et al. as mentioned in this paper developed a spatiotemporal regression kriging model to map daily high-resolution (3-km) ground NO2 concentrations in China using the Tropospheric Monitoring Instrument (TROPOMI) satellite retrievals and geographical covariates.
27 citations
TL;DR: Estimation results further confirm that the seasonal influences in coastal areas are much more significant than the interannual effects, which demonstrates that extending the GTWR model to handle both spatiotemporal heterogeneity and seasonal variations are meaningful.
26 citations
TL;DR: A spatial proximity neural network (SPNN) model was proposed in this paper to address the nonlinear effects of spatial anisotropy and achieved a better fitting accuracy and a more adequate prediction ability than ordinary linear regression (OLR), geographically weighted regression (GWR), GNNWR, and anisotropic-based GWR models.
18 citations
Cited by
More filters
TL;DR: Wang et al. as mentioned in this paper employed an extended ensemble learning of the space-time extremely randomized trees (STET) model, together with ground-based observations, remote sensing products, atmospheric reanalysis, and an emission inventory.
109 citations
TL;DR: Wang et al. as mentioned in this paper used an extended ensemble learning of the space-time extremely randomized trees (STET) model, together with ground-based observations, remote sensing products, atmospheric reanalysis, and an emission inventory, to estimate ground-level ozone from solar radiation intensity and surface temperature.
87 citations
01 Apr 2013
TL;DR: In this article, a numerical model based on the Regional Ocean model System (ROMS) was proposed to find out the dominant phosphate origin as well as the underlying forcing mechanism in summer algal blooms.
Abstract: Off the coast of Zhejiang province, China, algal blooms are frequently observed where the phosphate seems to be an essential ingredient to dominate the growth of the phytoplankton in summer. Therefore, the observed high phosphate distributions off the coast of Zhejiang are closely examined to find out the dominant phosphate origin as well as the underlying forcing mechanism in summer. The observed phosphate distribution has been faithfully reproduced by our numerical model based on the Regional Ocean model System (ROMS). Then, on the basis of the numerical experiments as well as the observations, we propose that the phosphate off the coast of Zhejiang mainly originates from the deep sea water in a special area (122.1 degrees E-z122.5 degrees E, 130 m-300 m deep) along 24.9 degrees N northeast of Taiwan. Also, the forcing mechanism is clearly illustrated. In the bottom water of southern East China Sea, huge phosphate is continuously transported to the area off the coast of Zhejiang by a nearshore Kuroshio branch current which links the phosphate-rich deep sea water to the bottom water off the coast of Zhejiang. Then, off the coast of Zhejiang the transported phosphate-rich water is further upwelled to the surface water due to an upwelling just off the coast of Zhejiang. Then, the upwelled phosphate-rich water is transported offshore in the surface water by the north-eastward flowing Taiwan Warm Current, forming a high phosphate tongue which can be easily utilized by the phytoplankton and then immediately explains the observed high chlorophyll tongue off the coast of Zhejiang. Crown Copyright (C) 2013 Published by Elsevier B.V. All rights reserved.
57 citations
TL;DR: In this paper, the authors presented and summarized the observed environmental effects of the COVID-19 pandemic as reported in the literature for different countries worldwide and provided a distinct overview considering the effects imposed on the air, water, wastewater and solid waste as critical elements of the environment.
52 citations
TL;DR: In this paper , the authors describe the cases in which machine learning algorithms have been applied to evaluate the water quality in different water environments, such as surface water, groundwater, drinking water, sewage, and seawater.
Abstract: With the rapid increase in the volume of data on the aquatic environment, machine learning has become an important tool for data analysis, classification, and prediction. Unlike traditional models used in water-related research, data-driven models based on machine learning can efficiently solve more complex nonlinear problems. In water environment research, models and conclusions derived from machine learning have been applied to the construction, monitoring, simulation, evaluation, and optimization of various water treatment and management systems. Additionally, machine learning can provide solutions for water pollution control, water quality improvement, and watershed ecosystem security management. In this review, we describe the cases in which machine learning algorithms have been applied to evaluate the water quality in different water environments, such as surface water, groundwater, drinking water, sewage, and seawater. Furthermore, we propose possible future applications of machine learning approaches to water environments. • Machine learning is widely used in water quality monitoring and prediction. • The performance of 45 machine learning algorithms is evaluated and discussed. • The challenges and opportunities of machine learning in water system are described.
47 citations