Predicting and analyzing the algal population dynamics of a grass-type lake with explainable machine learning.

Algal blooms, exacerbated by climate change and eutrophication, have emerged as a global concern. In this study, we introduce a novel interpretable machine learning (ML) workflow tailored for investigating the dynamics of algal populations in grass-type lakes, Liangzi lake. Utilizing seven ML methods and incorporating the covariance matrix adaptation evolution strategy (CMA-ES), we predict algal density across three distinct time periods, resulting in the construction of a total of 30 ML models. The CMA-ES-CatBoost model consistently demonstrates superior predictive accuracy and generalization capability across these periods. Through the collective validation of various interpretable tools, we identify water temperature and permanganate index as the two most critical water quality parameters (WQIs) influencing algal density in Liangzi Lake. Additionally, we quantify the independent and interactive effects of WQIs on algal density, pinpointing key thresholds and trends. Furthermore, we determine the minimum combination of WQIs that achieves near-optimal predictive performance, striking a balance between accuracy and cost-effectiveness. These findings offer a scientific and economically efficient foundation for governmental agencies to formulate strategies for water quality management and sustainable development.

Effects of grass type on hydraulic response of the three-layer landfill cover system.

Soil column tests were conducted to investigate the effects of grass type on water infiltration in a three-layer landfill cover under drying and wetting conditions. Five soil columns were prepared, including one bare, two Bermuda grass-planted and the other two vetiver-planted. During the drying period, the suction of vetiver-planted soil column was the largest, while that of bare case was the lowest. During the wetting period, the infiltration rate shows a bimodal form due to the contrasting hydraulic properties of different soil layers. The infiltration rate of vetiver-planted soil column was the lowest, followed by Bermuda grass-planted and bare cases. Correspondingly, the vetiver-planted soil column retained the maximum suction and the deepest ponding depth during rainfall. This was likely due to the larger leaf area and deeper roots of vetiver than those of Bermuda grass, thus inducing the maximum initial suction by root water uptake before rainfall and reducing the water permeability by root occupations of soil pores. These results show that vetiver is more effective than Bermuda grass to reduce water percolation through the three-layer landfill cover.

One-year monitoring of grass-type architectural waterscapes with long-term operation: Water quality and microorganism.

Grass-type architectural waterscapes (GAWs) utilize submerged plants to enhance self-purification ability and maintain a clear-water state. However, knowledge about their long-term water quality and microbial community dynamics remains limited. This study monitored the water quality, microbial community composition, and networks in two GAWs. GAW1 consisted solely Hydrilla verticillata with a water depth of 0.70 m, while GAW2 primarily contained Vallisneria natans, Microsorum pteropus, and Aquarius grisebachii with a water depth of 0.30 m. Results show that both water depth and submerged plant species play crucial roles in GAW establishment. The water depth of 0.7 m enabled Hydrilla verticillata to thrive underwater despite temperature variations, which demonstrated excellent nutrient uptake capacity. Thus, GAW1 exhibited superior self-purification ability, consistently meeting Class III standard for surface water in China. In contrast, GAW2 had a shallow water depth and contained ornamental plants, only meeting Class V standard. Furthermore, microbial communities were shaped by water quality, with distinct enriched genera serving as potential "microbial indicators". Enrichment of the hgcI clade and Sporichthyaceae_unclassified indicated superior water quality in GAW1, while prevalence of Comamonadaceae_unclassified, Flavobacterium, Rhodoluna, and Pseudarcicella suggested poor water quality in GAW2. Additionally, highly complex and connected microbial networks suggested elevated pollutant levels in GAWs. This study emphasized the significance of submerged plant species and water depth in GAWs construction and highlighted microbial communities and networks as potential indicators of water quality.

The Effects of Vegetation Type on Oedaleus decorus asiaticus (Orthoptera: Acrididae) Oviposition and Hatching Success.

Oedaleus decorus asiaticus (Bei-Bienko, 1941) has been regarded as one of the most dominant locusts in the northern grassland, the adjacent area of agriculture and animal farmland, in China. The aims of this study were to investigate the effects of vegetation type on the oviposition behavior of this pest in an open field and the hatching success of the offspring in the following year. The results showed that vegetation type did have a significant effect on whether any egg pods were laid by O. d. asiaticus. Once the females laid eggs, vegetation type and cage number had a significant effect on the number of egg pods laid. The highest number of egg pods was found in the Cleistogenes squarrosa treatment, followed by Stipa krylovii and then Leymus chinensis, while the Artemisia frigida treatment contained the lowest number of egg pods. The O. d. asiaticus eggs laid in S. krylovii and C. squarrosa treatments had a significantly higher hatching success rate (over 53%) than the other two grasses (below 40%). In short, habitats with C. squarrosa and S. krylovii grasses are likely to be preferred by ovipositing females, thus population monitoring efforts of O. d. asiaticus should focus on these habitats.