The spatiotemporal patterns and shifts of net ecosystem productivity (NEP) play a pivotal role in ecological conservation and addressing climate change. For example, by quantifying the NEP information within ecosystems, we can achieve the protection and restoration of natural ecological balance. Monitoring the changes in NEP enables a more profound understanding and prediction of ecosystem alterations caused by global warming, thereby providing a scientific basis for formulating policies aimed at mitigating and adapting to climate change. The accurate prediction of NEP sheds light on the ecosystem’s response to climatic variations and aids in formulating targeted carbon sequestration policies. While traditional ecological process models provide a comprehensive approach to predicting NEP, they often require extensive experimental and empirical data, increasing research costs. In contrast, machine-learning models offer a cost-effective alternative for NEP prediction; however, the delicate balance in algorithm selection and hyperparameter tuning is frequently overlooked. In our quest for the optimal prediction model, we examined a combination of four mainstream machine-learning algorithms with four hyperparameter-optimization techniques. Our analysis identified that the backpropagation neural network combined with Bayesian optimization yielded the best performance, with an R² of 0.68 and an MSE of 1.43. Additionally, deep-learning models showcased promising potential in NEP prediction. Selecting appropriate algorithms and executing precise hyperparameter-optimization strategies are crucial for enhancing the accuracy of NEP predictions. This approach not only improves model performance but also provides us with new tools for a deeper understanding of and response to ecosystem changes induced by climate change.

Clay-based adsorbent materials are widely used to remove heavy metal ions from water. In this study, we have fabricated a novel composite material, consisting of rectorite and sludge-derived biochar (REC/SDBC), and characterized its effectiveness in removing lead from water. Our SEM images show that the REC is evenly dispersed on the surface of the SDBC. The composites have a mesoporous structure, and its BET surface is (16.5 m²/g) comparable with that of SDBC but larger than that of REC. We found that the maximum adsorption capacity for Pb(II) was 26.89 mg g⁻¹ for REC/SDBC composites with a REC:SDBC ratio of 3:1, which was achieved within 120 min. This is higher than the adsorption capacities of REC (19.81 mg g⁻¹) and SDBC (23.15 mg g⁻¹) alone. Furthermore, we observed that the adsorption capacity was greater at pH 5.0 compared to other pH values. Our results also indicate that the pseudo-second-order model and the Langmuir isotherm model provide good fits for the rates and isotherms of Pb(II) adsorption onto REC/SDBC composites. The adsorption kinetic constant and the Langmuir adsorption constant were calculated to be 0.0065 g mg⁻¹ min⁻¹ and 0.319 L mg⁻¹, respectively. X-ray photoelectron spectroscopy analysis confirmed that the reaction mechanism is mainly dominated by chemisorption, involving cationic exchange, surface complexation, and surface precipitation. The high adsorption capacity, combined with the cost-effectiveness and environmental-friendly nature of REC/SDBC composites, make them promising candidates for removing heavy metallic elements from wastewater.