Are more data always better? - Machine learning forecasting of algae based on long-term observations.

Bloom-forming algae present a unique challenge to water managers as they can significantly impair provision of important ecosystem services and cause health risks to humans and animals. Consequently, effective short-term algae forecasts are important as they provide early warnings and enable implementation of mitigation strategies. In this context, machine learning (ML) emerges as a promising forecasting tool. However, the performance of ML models is heavily dependent on the availability of appropriate training data. Consequently, it is essential to determine the volume of data necessary to develop reliable ML forecasts. Understanding this will guide future monitoring strategies, optimize resource allocation, and set realistic expectations for management outcomes. In this study, we used 30 years of fortnightly measurements of 13 different parameters from a lake in the English Lake District (UK) to examine the impact of training data duration on the performance of ML models for forecasting chlorophyll-a two weeks in advance. Once training data availability exceeded four years, a Random Forest model was found to consistently outperform naive benchmarks (mean absolute percentage error 16.4 % lower than the best-performing benchmark). With more than 5 years of training data, model performance generally continued to improve, but with diminishing returns. Furthermore, it was found that equivalent and, in some cases, better performance could be achieved by only using a subset of the most important input features. Additionally, it was found that reducing the sampling frequency had negative impacts on performance, both due to the reduced number of training observations available, and increased forecast horizon. Our findings demonstrate that for lakes ecologically similar to the study site, a consistent and regular sampling programme focused on monitoring a limited number of key parameters can provide sufficient observations for generating short-term algae forecasts after approximately five years of data collection. Importantly, this result provides justification for the initiation of new monitoring programmes for sites where algal blooms are a concern, and suggests that there are likely many pre-existing monitoring datasets which would be suitable for training algae forecast models.

被引量：- 发表：1970

Constructed wetlands using recycled aggregates for the improved treatment of tailwater.

Recycled aggregates from the construction industry could be effective materials for constructed wetland (CW) wastewater treatment systems. However, whether the plants or which kinds of plants can survive in CWs with recycled aggregates or not is still scarce and urgent to study. The effects of different plant species, and several operation parameters on tailwater treatment from the sewage plants by CWs with different substrates (mixed construction recycled aggregate [MCRA], red brick [RB], and gravel) are systemically studied. The results showed that the average removal efficiencies of the chemical parameters in MCRA-CWs with seven plants, such as Cyperus alternifolius, were higher than those of RB-CWs and Gravel-CWs. In the MCRA-CWs, the average removal efficiencies of Typha orientalis, Cyperus alternifolius, and Phragmites australis were 77.58%, 75.09%, and 73.16%, respectively, which were higher than those of the other plants. Meanwhile, Proteobacteria had the highest relative abundances in MCRA and RB at 54.98% and 69.22%, respectively, whereas Cyanobacteria (35.21%) were the most abundant in the gravel. The influence of season on water purification was significant (p < 0.05) in the MCRA. Overall, water quality purification was dependent on season, HRT, and C/N, which accounted for 86.1%, 13%, and 7.1%, respectively. The highest average removal efficiencies of the MCRA-CWs were 71.98% (COD), 85.58% (NH4+-N), 95.01% (TN), and 84.11% (TP) when the HRT was 3 d and C/N ratio was 2.5 in the summer. This indicates that treated recycled construction aggregates could be used as substrates in CWs and have both wastewater purification and environmental improvement effects, thus achieving the purpose of "treating the wastes with wastes".

被引量：- 发表：1970

A hybrid system based on the combination of adsorption, electrocoagulation, and wetland treatment for the effective remediation of industrial wastewater from underground coal gasification (UCG).

The study verified the effectiveness of treating post-process underground coal gasification (UCG) wastewater, containing high loads of inorganic and organic pollutants, using constructed wetlands (CW) enhanced by hybrid adsorption and electrocoagulation (EC) techniques. Four different system configurations were tested: wetland, EC/wetland, adsorbent/wetland, and EC/adsorbent/wetland. Each experiment lasted 60 days. The feed and effluents from each treatment step were analysed for their basic physicochemical parameters such as metals and trace elements, phenols, sulphides, cyanides, total organic carbon (TOC), chemical oxygen demand (COD), biological oxygen demand (BOD), benzene, toluene, ethylene, xylene (BTEX), and polyaromatic hydrocarbons (PAHs). Systems with electrocoagulation proved to be effective in the case of metal removal. The best results were obtained for Fe, Ni, Sb and As (up to 96%, 98%, 94% and 82% respectively). The systems were ineffective in removing Mn. All tested systems showed the greatest effectiveness in the treatment of wastewater from phenols, BTEX and CN (almost 100% removal). CWs without preliminary electrocoagulation showed practically 100% effectiveness in removing BTEX after 14 days of treatment. Electrocoagulation was particularly effective in reduction of large quantity of PAH compounds (from 1228 μg/l to below 0.050 μg/l). Effective toxicity reduction from V class to II class after 60 days in comparison with meeting the requirements contained in the Best Available Techniques (BAT) document, showed that all tested systems were favorable in terms of UCG wastewater treatment. A significant decrease in toxicity was observed in just 14 days (around 90% reduction of toxicity measured in TU values for systems without adsorbent and around 75% for systems with adsorbent). The wastewater were still toxic due to the formation of degradation intermediates of organic compounds (BTEX, PAHs, phenol compounds), despite a significant decrease in the concentration of contaminants, therefore toxicity assessment should be one of the evaluation criteria for industrial wastewater treatment.

被引量：- 发表：1970

Smart, sustainable, and circular port maintenance: A comprehensive framework and multi-stakeholder approach.

被引量：- 发表：1970

Fluoride removal using a rotating anode electro-coagulation reactor: Parametric optimization using response surface methodology, isotherms and kinetic studies, economic analysis and sludge characterization.

被引量：- 发表：1970