Coastal water quality prediction based on machine learning with feature interpretation and spatio-temporal analysis

Grbčić, Luka; Družeta, Siniša; Mauša, Goran; Lipić, Tomislav; Lušić, Darija Vukić; Alvir, Marta; Lučin, Ivana; Sikirica, Ante; Davidović, Davor; Travaš, Vanja; Kalafatović, Daniela; Pikelj, Kristina; Fajković, Hana; Holjević, Toni; Kranjčević, Lado

doi:10.1016/j.envsoft.2022.105458

Cited by 29 publications

(15 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Given the large number of zooplankton species (variables in the model), we used an innovative method of clustering to obtain detailed information about their response to changes in water temperature in winter. When comparing our work with similar studies using SHAP 38 , 39 modelling, it should be noted that we applied the final averaging of a pool of five models with the Shapley value results (Figs. 3 and 4 ).…”

Section: Discussionmentioning

confidence: 99%

“…To this end, we added modelling with SHapley Additive exPlanations (SHAP) to the boosting model. This algorithm was used to calculate and visualise individualised interactions between environmental variables in the analysis of feature selection for stream water quality monitoring 38 , the prediction of microbiological water quality of coastal waters 39 and the analysis of the sensitivity of environmental parameters of lagoon waters to annual weather changes 40 . In our study SHAP modelling was used to assess the effects of winter warming based on the interactions between the biomass of zooplankton species in the two thermal artificial lake types.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Predicting the effects of winter water warming in artificial lakes on zooplankton and its environment using combined machine learning models

Kruk

Goździejewska

Artiemjew

2022

Sci Rep

View full text Add to dashboard Cite

This work deals with the consequences of climate warming on aquatic ecosystems. The study determined the effects of increased water temperatures in artificial lakes during winter on predicting changes in the biomass of zooplankton taxa and their environment. We applied an innovative approach to investigate the effects of winter warming on zooplankton and physico-chemical factors. We used a modelling scheme combining hierarchical clustering, eXtreme Gradient Boosting (XGBoost) and SHapley Additive exPlanations (SHAP) algorithms. Under the influence of increased water temperatures in winter, weight- and frequency-dominant Crustacea taxa such as Daphnia cucullata, Cyclops vicinus, Cryptocyclops bicolor, copepodites and nauplii, and the Rotifera: Polyarthra longiremis, Trichocerca pusilla, Keratella quadrata, Asplanchna priodonta and Synchaeta spp. tend to decrease their biomass. Under the same conditions, Rotifera: Lecane spp., Monommata maculata, Testudinella patina, Notholca squamula, Colurella colurus, Trichocerca intermedia and the protozoan species Centropyxis acuelata and Arcella discoides with lower size and abundance responded with an increase in biomass. Decreases in chlorophyll a, suspended solids and total nitrogen were predicted due to winter warming. Machine learning ensemble models used in innovative ways can contribute to the research utility of studies on the response of ecological units to environmental change.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Predicting the effects of winter water warming in artificial lakes on zooplankton and its environment using combined machine learning models

Kruk

Goździejewska

Artiemjew

2022

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Compared with other algorithms like SVM and KNN, the DT provides better results that are effective for the prediction (Huynh-Cam et al, 2021). Unlike the Recently, several studies have also revealed that the XGB algorithm is effective for predicting WQIs (Grbčić et al, 2021;Huan et al, 2020;Islam Khan et al, 2021;Uddin et al, 2022b). Because the ensemble based algorithms combine multiple DTs and consider the average of the output of all DTs for the prediction (Malek et al, 2022).…”

Section: Discussionmentioning

confidence: 99%

“…For example, research on predicting water quality has revealed that the ML algorithm could be more effective in evaluating water quality than other traditional methods (Aldhyani et al, 2020;Azrour et al, 2021;Babbar and Babbar, 2017;Haghiabi et al, 2018a;Mohammed et al, 2018;Prakash et al, 2018;Solanki et al, 2015;Xiong et al, 2020). Several studies have effectively used machine learning approaches to predict WQI (Ahmad et al, 2017;Bui et al, 2020;Grbčić et al, 2021;Hassan et al, 2021;Kadam et al, 2019;Kouadri et al, 2021;Leong et al, 2019;Venkata Vara Prasad et al, 2020;Wang et al, 2017). This research utilized eight ML algorithms to identify robust algorithms for predicting WQM-WQIs.…”

Section: Machine Learning Algorithmsmentioning

confidence: 99%

“…They suggest that tree-based algorithms are practical for predicting WQIs. Some studies recommend that ensemble tree-based algorithms such as extreme gradient boosting (XGB) and random forest (RF) are potentially useful for predicting WQIs (Grbčić et al, 2021;Haghiabi et al, 2018a;Islam Khan et al, 2021;Khullar and Singh, 2021). Moreover, researchers successfully applied AI-based algorithms like support vector machine (SVM), least square SVM (LSVM) and artificial neural network for predicting WQIs (Aldhyani et al, 2020;Haghiabi et al, 2018b;Pham et al, 2019;Prasad et al, 2022;Wu and Wang, 2022).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Robust Machine Learning Algorithms for Predicting Coastal Water Quality Index

Uddin

Diganta

Rahman³

et al. 2022

SSRN Journal

View full text Add to dashboard Cite

Forecasting bathing water quality in the UK: A critical review

Krupska,

Speight,

Robinson

et al. 2024

WIREs Water

View full text Add to dashboard Cite

Climate change is altering rainfall patterns resulting in increasing variability and intensity of rainfall events worldwide. Increases to short duration, intense rainfall (i.e., convective rainfall), will lead to increases in sewage overflow and run‐off from agricultural land. Such events generate spikes in micro‐organisms from feces and manure, especially Escherichia coli and intestinal enterococci, that temporarily end up in bathing waters posing serious health risks to bathers. Forecasting of bathing water quality associated with convective rainfall presents a distinctive forecasting challenge due to high uncertainties associated with predicting the timing, location, and impact of such events. In this article, we review examples of bathing water quality forecasting practices, with a focus on the United Kingdom where convective rainfall in the summer bathing water season is a particular concern, and question whether the current approach is robust in a changing climate. We discuss potential upgrades in bathing water forecasting and identify the main challenges that must be addressed before an improved framework for bathing water forecasting can be achieved. Although developments in meteorological and hydrological short‐range forecasting capabilities are promising, convective rainfall forecasting has significant predictability limits. We suggest taking full advantage of short‐range forecasts to provide sub‐daily bathing water forecasts, focusing on targeted bathing water monitoring regimes to improve model accuracy with the ultimate goal of providing improved information and guidance for beach users.This article is categorized under: Science of Water > Water and Environmental Change Human Water > Water Governance Science of Water > Water Quality

show abstract

Coastal water quality prediction based on machine learning with feature interpretation and spatio-temporal analysis

Cited by 29 publications

References 40 publications

Predicting the effects of winter water warming in artificial lakes on zooplankton and its environment using combined machine learning models

Predicting the effects of winter water warming in artificial lakes on zooplankton and its environment using combined machine learning models

Robust Machine Learning Algorithms for Predicting Coastal Water Quality Index

Forecasting bathing water quality in the UK: A critical review

Contact Info

Product

Resources

About