Joint estimation of PM_(2.5) and O_(3) over China using a knowledge-informed neural network

China has currently entered a critical stage of coordinated control of fine particulate matter(PM_(2.5))and ozone(O_(3)),it is thus of tremendous value to accurately acquire high-resolution PM_(2.5) and O_(3) data.In contrast to traditional studies that usually separately estimate PM_(2.5) and O_(3),this study proposes a knowledge-informed neural network model for their joint estimation,in which satellite observations,reanalysis data,and ground station measurements are used.The neural network architecture is designed with the shared and specific inputs,the PM_(2.5)-O_(3) interaction module,and the weighted loss function,which introduce the prior knowledge of PM_(2.5) and O_(3) into neural network modeling.Cross-validation(CV)results indicate that the inclusion of prior knowledge can improve the estimation accuracy,with R^(2) increasing from 0.872 to 0.911 and from 0.906 to 0.937 for PM_(2.5) and O_(3) estimation under samplebased CV,respectively.In addition,the proposed joint estimation model achieves comparable performance with the separate estimation model,but with higher efficiency.Mapping results of PM_(2.5) and O_(3) derived by the proposed model have demonstrated interesting findings in the spatial and temporal trends and variations over China.

An improved knowledge-informed NSGA-II for multi-objective land allocation (MOLA)

Multi-objective land allocation(MOLA)can be regarded as a spatial optimization problem that allocates appropriate use to certain land units subjecting to multiple objectives and constraints.This article develops an improved knowledge-informed non-dominated sorting genetic algorithm II(NSGA-II)for solving the MOLA problem by integrating the patch-based,edge growing/decreasing,neighborhood,and constraint steering rules.By applying both the classical and the knowledge-informed NSGA-II to a simulated planning area of 30×30 grid,we find that:when compared to the classical NSGA-II,the knowledge-informed NSGA-II consistently produces solutions much closer to the true Pareto front within shorter computation time without sacrificing the solution diversity;the knowledge-informed NSGA-II is more effective and more efficient in encouraging compact land allocation;the solutions produced by the knowledge-informed have less scattered/isolated land units and provide a good compromise between construction sprawl and conservation land protection.The better performance proves that knowledge-informed NSGA-II is a more reasonable and desirable approach in the planning context.