As wind energy development increases, accurate wind energy forecasting helps to develop sensible power generation plans and ensure a balance between supply and demand. Machine-learning-based forecasting models possess exceptional predictive capabilities, and data manipulation prior to model training is also a key focus of this research. This study trained a deep Long Short-Term Memory (LSTM) neural network to learn the processing results of the Savitzky-Golay filter, which can avoid overfitting due to fluctuations and noise in measurements, improving the generalization performance. The optimum data frame length to match the second-order filter was determined by comparison. In a single-step prediction, the method reduced the root-mean-square error by 3.8% compared to the model trained directly with the measurements. The method also produced the smallest errors in all steps of the multi-step advance prediction. The proposed method ensures the accuracy of the forecasting and, on that basis, also improves the timeliness of the effective forecasts.

Facing the global freshwater resource crisis, using solar energy to produce fresh water resources in an environmentally friendly way, sorption-based atmospheric water harvesting driven by solar technology has attracted increasingly more attention. In the current research, the adsorbent MOF-801 has the advantages of a high adsorption capacity and is suitable for fields with a wide range of humidity. However, the strong interaction between the adsorbent and water molecules is conducive to rapid moisture absorption, but at the same time, the adsorbent needs higher heat to achieve regeneration, which restricts the practical application of the adsorbent. Based on the principle that carbon materials can improve the photothermal conversion performance of adsorbent, this paper prepared three composite adsorbents with MOF-801 and three different carbon materials, characterized the structure and morphology of each adsorbent, and compared the effects of different carbon materials on the performance of MOF-801 adsorbent. Among them, the photothermal characteristics of MOF-801/CNT adsorbent proposed in this paper are most significantly improved. The experiment shows that compared with MOF-801/G, the adsorption capacity is increased by 30%, and the desorption speed is increased by 50%. It maximizes water withdrawals over a period of time in arid environments.