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

Abstract

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.

The response of zooplankton network indicators to winter water warming using shallow artificial reservoirs as model case study

“…Thus, populations of zooplankton species characterised by smaller size, lower weight and lower nutrient requirements increased in their biomass. Ejsmont-Karabin et al 44 and Kruk et al 39 also reported a positive correlation between psammophilous-epiphytic Rotifera and increased and stable water temperature in heated lakes. Other authors observed that the growth of small crustacean species was accelerated by an increase in water temperature 5,26,47,48 .…”

“…in MW and 9.2°C in WW), algal blooms were less frequent and primary production was lower 39,63 . It is worth noting that the variability of water temperature in the studied reservoirs was the most important factor that distinguished these water bodies (Fig.…”

“…Therefore, species-speci c responses to changes in the thermal regime are directly re ected in the taxonomic structure, biomass and functional properties of zooplankton communities 25,26,39,53 . These factors affect the organisation of interspeci c relationships in zooplankton networks, which consist mainly of competition and predation, and they in uence successive trophic levels 43,54,55 .…”

Explainable Artificial Intelligence in the Early Diagnosis of Gastrointestinal Disease

“…Moreover, the notion of explainable artificial intelligence is enjoying immense popularity now. Explainable artificial intelligence can be defined as “artificial intelligence to identify major predictors of the dependent variable”, and there are four approaches of explainable artificial intelligence at this point, i.e., random forest impurity importance, random forest permutation importance [ 20 , 21 ], machine learning accuracy importance, and Shapley additive explanations (SHAP) [ 15 , 22 , 23 , 24 , 25 , 26 , 27 , 28 , 29 , 30 , 31 , 32 ]. Random forest impurity importance calculates the node impurity decrease from the creation of a branch on a certain predictor.…”

“…Machine learning accuracy importance (an extension of random forest permutation importance) calculates the accuracy decrease from the exclusion of data on the predictor. The SHAP value of a predictor for a participant measures the difference between what machine learning predicts for the probability of GID with and without the predictor [ 15 , 22 , 23 , 24 , 25 , 26 , 27 , 28 , 29 , 30 , 31 , 32 ]. For example, let us assume in a hypothetical figure ( Figure 1 ) that the SHAP values of diabetes (x033) for GERD have the range of (−0.05, 0.30).…”