Evaluation of a Modified Monod Model for Predicting Algal Dynamics in Lake Tai

An Improved Transfer Learning Model for Cyanobacterial Bloom Concentration Prediction

The outbreak of cyanobacterial blooms is a serious water environmental problem, and the harm it brings to aquatic ecosystems and water supply systems cannot be underestimated. It is very important to establish an accurate prediction model of cyanobacterial bloom concentration, which is a challenging issue. Machine learning techniques can improve the prediction accuracy, but a large amount of historical monitoring data is needed to train these models. For some waters with an inconvenient geographical location or frequent sensor failures, there are not enough historical data to train the model. To deal with this problem, a fused model based on a transfer learning method is proposed in this paper. In this study, the data of water environment with a large amount of historical monitoring data are taken as the source domain in order to learn the knowledge of cyanobacterial bloom growth characteristics and train the prediction model. The data of the water environment with a small amount of historical monitoring data are taken as the target domain in order to load the model trained in the source domain. Then, the training set of the target domain is used to participate in the inter-layer fine-tuning training of the model to obtain the transfer learning model. At last, the transfer learning model is fused with a convolutional neural network to obtain the prediction model. Various experiments are conducted for a 2 h prediction on the test set of the target domain. The results show that the proposed model can significantly improve the prediction accuracy of cyanobacterial blooms for the water environment with a low data volume.

Reactive Transport: A Review of Basic Concepts with Emphasis on Biochemical Processes

Reactive transport (RT) couples bio-geo-chemical reactions and transport. RT is important to understand numerous scientific questions and solve some engineering problems. RT is highly multidisciplinary, which hinders the development of a body of knowledge shared by RT modelers and developers. The goal of this paper is to review the basic conceptual issues shared by all RT problems, so as to facilitate advancement along the current frontier: biochemical reactions. To this end, we review the basic equations to indicate that chemical systems are controlled by the set of equilibrium reactions, which are easy to model, but whose rate is controlled by mixing. Since mixing is not properly represented by the standard advection-dispersion equation (ADE), we conclude that this equation is poor for RT. This leads us to review alternative transport formulations, and the methods to solve RT problems using both the ADE and alternative equations. Since equilibrium is easy, difficulties arise for kinetic reactions, which is especially true for biochemistry, where numerous challenges are open (how to represent microbial communities, impact of genomics, effect of biofilms on flow and transport, etc.). We conclude with the basic eleven conceptual issues that we consider fundamental for any conceptually sound RT effort.

Effects of hydrological and climatic variables on cyanobacterial blooms in four large shallow lakes fed by the Yangtze River

Shallow lakes, one of the most widespread water bodies in the world, are easily shifted to a new trophic state due to external interferences. Shifting hydrologic conditions and climate change can cause cyanobacterial harmful algal blooms (CyanoHABs) in shallow lakes, which pose serious threats to ecological integrity and human health. This study analyzed the effects of hydrologic and meteorological variables on cyanobacterial blooms in Yangtze-connected lakes (Lake Dongting and Poyang) and isolated lakes (Lake Chao and Tai). The results show that (i) chlorophyll-a (Chl-a) concentration tends to decrease exponentially with increasing relative lake level fluctuations (RLLF) and precipitation, but to increase linearly with increasing wind speed and air temperature; (ii) Chl-a concentrations in lakes were significantly higher when RLLF < 100, precipitation < 2.6 mm, wind speed > 2.6 m s^-1, or air temperature > 17.8 °C; (iii) the Chl-a concentration of Yangtze-isolated lakes was more significantly affected by water level amplitude, precipitation, wind speed and air temperature than the Yangtze-connected lakes; (iv) the RLLF and the ratio of wind speed to mean water depth could be innovative coupling factors to examine variation characteristics of Chl-a in shallow lakes with greater correlation than single factors.

Modelling eutrophication in lake ecosystems: A review

Eutrophication is one of the main causes of the degradation of lake ecosystems. Its intensification during the last decades has led the stakeholders to seek for water management and restoration solutions, including those based on modelling approaches. This paper presents a review of lake eutrophication modelling, on the basis of a scientific appraisal performed by researchers for the French ministries of Environment and Agriculture. After a brief introduction presenting the scientific context, a bibliography analysis is presented. Then the main results obtained with process-based models are summarized. A synthesis of the scientist recommendations in order to improve the lake eutrophication modelling is finally given before the conclusion.