Five Most Recent Research Works on Autocorrelation in Water Resource Management
Autocorrelation is the correlation between two part of a single data series and is useful when the trendability of a parameter is approximated with the help of data. Most used in water research study.
Auto-correlation is defined as a relationship identification metric which is used to identify the correlation between the two halves of a single data series. For example, if the relationship between the January to June month rainfall average is compared with the July to December rainfall then the correlation between the two is known as Auto or Serial Correlation.
You may see the following video to have a concept of the metrics and to know how to find the autocorrelation :
In this article five most recent research studies on autocorrelation in water resource development are depicted to have an idea of the recent development of the metrics.
Articles were chosen based on the date of publication and the reputation of the journal where it is published.
Time-sensitive prediction of NO2 concentration in China using an ensemble machine learning model from multi-source data.
Nitrogen dioxide (NO2) poses a critical potential risk to environmental quality and public health. A reliable machine learning (ML) forecasting framework will be useful to provide valuable information to support government decision-making. Based on the data from 1609 air quality monitors across China from 2014-2020, this study designed an ensemble ML model by integrating multiple types of spatial-temporal variables and three sub-models for time-sensitive prediction over a wide range. The ensemble ML model incorporates a residual connection to the gated recurrent unit (GRU) network and adopts the advantage of Transformer, extreme gradient boosting (XGBoost) and GRU with residual connection network, resulting in a 4.1%±1.0% lower root mean square error over XGBoost for the test results. The ensemble model shows great prediction performance, with coefficient of determination of 0.91, 0.86, and 0.77 for 1-hr, 3-hr, and 24-hr averages for the test results, respectively. In particular, this model has achieved excellent performance with low spatial uncertainty in Central, East, and North China, the major site-dense zones. Through the interpretability analysis based on the Shapley value for different temporal resolutions, we found that the contribution of atmospheric chemical processes is more important for hourly predictions compared with the daily scale predictions, while the impact of meteorological conditions would be ever-prominent for the latter. Compared with existing models for different spatiotemporal scales, the present model can be implemented at any air quality monitoring station across China to facilitate achieving rapid and dependable forecast of NO2, which will help developing effective control policies.
Reference: Chenliang Tao, Man Jia, Guoqiang Wang, Yuqiang Zhang, Qingzhu Zhang, Xianfeng Wang, Qiao Wang, Wenxing Wang,2024, Time-sensitive prediction of NO2 concentration in China using an ensemble machine learning model from multi-source data, Journal of Environmental Sciences, Volume 137,2024, Pages 30-40, ISSN 1001-0742,https://doi.org/10.1016/j.jes.2023.02.026.
Comprehensive study on the spatial distribution of heavy metals and their environmental risks in high-sulfur coal gangue dumps in China
The accumulation of coal gangue (CG) from coal mining is an important source of heavy metals (HMs) in soil. Its spatial distribution and environment risk assessment are extremely important for the management and remediation of HMs. Eighty soil samples were collected from the high-sulfur CG site in northern China and analyzed for six HMs. The results showed that the soil was heavily contaminated by Mn, Cr and Ni based on the Nemerow index, and posed seriously ecological risk depended on the geo-accumulation index, potential ecological risk index and risk assessment code. The semi-variogram model and ordinary kriging interpolation accurately portrayed the spatial distribution of HMs. Fe, Mn, and Cr were distributed by band diffusion, Ni was distributed by core, the distribution of Cu had obvious patchiness and Zn was more uniform. The spatial autocorrelation indicated that all HMs had strong spatial heterogeneity. The BCR sequential extraction was employed to qualify the geochemical fractions of HMs. The data indicated that Fe and Cr were dominated by residual fraction; Cu, Ni and Zn were dominated by reducible and oxidizable fractions; Mn was dominated by reducible and acid-extractable (25.38%-44.67%) fractions. Pearson correlation analysis showed that pH was the main control factor affecting the non-residue fractions of HMs. Therefore, acid production from high sulfur CG reduced soil pH by 2-3, which indirectly promoted the activity of HMs. Finally, the conceptual model of HMs contamination at the CG site was proposed, which can be useful for the development of ecological remediation strategies.
References : Dong, Yingbo, Huan Lu, and Hai Lin. "Comprehensive study on the spatial distribution of heavy metals and their environmental risks in high-sulfur coal gangue dumps in China." Journal of Environmental Sciences 136 (2024): 486-497.
Data-driven surrogate modeling: Introducing spatial lag to consider spatial autocorrelation of flooding within urban drainage systems
Data-driven surrogate modeling has been increasingly employed for flooding simulation of urban drainage systems (UDSs) due to its high computational efficiency and accuracy. However, spatial autocorrelation is prevalent in many typical scenarios, including the UDS. This omission of spatial information is very likely to cause the machine learning model to capture the wrong UDS overflow mechanism from the data. To capture the spatial autocorrelation, an artificial neural network (ANN)-based surrogate modeling method that introduces spatial lag to account for the spatial autocorrelation of flooding within the UDS is proposed and coupled with a genetic algorithm (GA) to reduce the uncertainty caused by random initialization of ANN. In this study, a surrogate modeling experiment was carried out for the Storm Water Management Model (SWMM). The experimental results show that the ANN can successfully capture the spatial autocorrelation induced by flooding within the UDS and accurately replicate the output simulated by SWMM.
References : Li, Heng, Chunxiao Zhang, Min Chen, Dingtao Shen, and Yunyun Niu. "Data-driven surrogate modeling: Introducing spatial lag to consider spatial autocorrelation of flooding within urban drainage systems." Environmental Modelling & Software (2023): 105623.
Effects of landscape characteristics, anthropogenic factors, and seasonality on water quality in Portland, Oregon
Urban areas often struggle with deteriorated water quality because of complex interactions between landscape factors and climatic variables. However, few studies have considered the effects of landscape variables on water quality at a sub-500-m scale. We conducted a spatial statistical analysis of six pollutants for 128 water quality stations in four watersheds around Portland, Oregon, using data from 2015 to 2021 for the wet season at two microscales (100 m and 250 m buffers). E. coli was associated with land cover, soil type, topography, and pipe length, while lead variations were best explained by topographic variables. Developed land cover and impervious surface explained variations in nitrate, while orthophosphate was associated with mean elevation. Models for zinc included land cover and topographic variables in addition to pipe length. Spatial regression models better explain variations in water quality than ordinary least squares models, indicating strong spatial autocorrelation for some variables. Our findings provide valuable insights to city planners and researchers seeking to improve water quality in metropolitan areas by manipulating city landscapes.
References : Gelsey, Katherine, Heejun Chang, and Daniel Ramirez. "Effects of landscape characteristics, anthropogenic factors, and seasonality on water quality in Portland, Oregon." Environmental Monitoring and Assessment 195, no. 1 (2023): 219.
Use of the water quality index and multivariate analysis to assess groundwater quality for drinking purpose in Ratnapura district, Sri Lanka
Groundwater is a key source of freshwater for communities in many nations, including Sri Lanka. However, with the current trends of population growth and climate change, stress on groundwater is increasing at an alarming rate. Groundwater quality in Sri Lanka has already been depleted over time as a result of both anthropogenic and natural factors, and there is a significant likelihood that such issues will get worse in the near future. The overall groundwater quality in Ratnapura district has not been the subject of any prior studies, despite the fact that many residents depend on groundwater as their primary source of water. Under these circumstances, this groundwater quality study was conducted to assess the groundwater quality in Ratnapura district with respect to the drinking water quality standards. In this study, available data on 10 water quality parameters from 50 groundwater sources was utilized to analyze the groundwater quality using several statistical and graphical methods. In particular, the Water Quality Index (WQI), geostatistical modeling, Hierarchical Cluster Analysis (HCA), Principal Component Analysis (PCA), and spatial autocorrelation analysis were used to assess the overall water quality and potential causes for variations over the area. Overall results revealed significant deterioration of groundwater quality in the eastern and south-eastern areas of the district. Multivariate analysis results revealed substantial differences between groundwater in the wet zone and the dry zone of the district, implying increased mineralization of groundwater in the dry zone. Furthermore, the results demonstrate that both climate and soil properties have a substantial impact on groundwater quality variation across the district. Future hydrogeological research in the area, as well as water engineers, policy makers, government officials, donor agencies, etc., will benefit from the findings of this study.
References : Karangoda, R. C., and K. G. N. Nanayakkara. "Use of the water quality index and multivariate analysis to assess groundwater quality for drinking purpose in Ratnapura district, Sri Lanka." Groundwater for Sustainable Development 21 (2023): 100910.
You may also like :
Very Short-Term Courses: Application of Analytical Hierarchy Process in Water Resource Management
Read the book: Probability and Statistics for Data Science & Machine Learning
Read the book : Statistics 101: From Data Analysis and Predictive Modeling to Measuring Distribution and Determining Probability
Become an Affiliate of the above and many other related books, courses, and products
Evaluate the suitability of a journal with respect to your article
Read the book: Lecture Notes on MCDM
Recommend papers, software, instruments, case studies, etc. for inclusion in the newsletter
HydroGeek may receive affiliate commissions from some of the links given above. All the commissions will be deposited to NGOs and NPOs after the deduction of the honorariums, maintenance, and taxes for running this site.
Follow me on Gumroad / Twitter / Listly
HydroGeek is a reader-supported publication. To support my work, consider becoming a paid subscriber or gift a subscription to someone you know will be interested in this newsletter.
Thanks for reading the entire article as a Thank You Gift I will increase the discount on the annual plan by 40%. Click on the button below to acquire the offer :