The prediction of PM2.5 concentration is a canonical predictive challenge due to the distribution of PM2.5 appears serious spatiotemporal variability at multiple scales. Currently, using satellite-based remote sensing data to estimate ground-level PM2.5 is a promising method for providing spatiotemporal continuous information of PM2.5. In this letter, we proposed a deep neural network (DNN)-based PM2.5 prediction model to capture the spatiotemporal variability of ground-level PM2.5 using the remote sensing aerosol optical depth (AOD) data from the Himawari-8 satellite along with the conventional meteorological observation variables (denoted as PM25-DNN). The PM25-DNN model was trained and tested using the data from Beijing-Tianjin-Hebei region of China in 2017, and we compared the prediction performance between the PM25-DNN and the current state-of-the-art methods in this field. The results show that the PM25-DNN outperforms the other models with the cross-validated coefficient of determination (R²), root-mean-square error (RMSE), mean prediction error (MPE), and relative prediction error (RPE) were 0.84, 19.9 μg/m³, 11.89 μg/m³, and 41.21%, respectively. Then, the trained PM25-DNN model was applied to estimate the hourly gridded PM2.5 with 1-km spatial resolution. Our results indicate that the DNN architecture can capture the essential spatiotemporal distribution associated with PM2.5 only using AOD data and conventional meteorological observational variables without more handcrafted features. The proposed PM25-DNN model can greatly improve the accuracy of PM2.5 estimation, and it provides a new perspective for PM2.5 monitoring using end-to-end deep learning method.

Airborne eddy covariance (EC) measurement is one of the most effective methods to directly measure the surface mass and energy fluxes at the regional scale. It offers the possibility to bridge the scale gap between local- and global-scale measurements by ground-based sites and remote-sensing instrumentations, and to validate the surface fluxes estimated by satellite products or process-based models. In this study, we developed an unmanned aerial vehicle (UAV)-based EC system that can be operated to measure the turbulent fluxes in carbon dioxides, momentum, latent and sensible heat, as well as net radiation and photosynthetically active radiation. Flight tests of the developed UAV-based EC system over land were conducted in October 2020 in Inner Mongolia, China. The in-flight calibration was firstly conducted to correct the mounting error. Then, three flight comparison tests were performed, and we compared the measurement with those from a ground tower. The results, along with power spectral comparison and consideration of the differing measurement strategies indicate that the system can resolve the turbulent fluxes in the encountered measurement condition. Lastly, the challenges of the UAV-based EC method were discussed, and potential improvements with further development were explored. The results of this paper reveal the considerable potential of the UAV-based EC method for land surface process studies.

Instrumentation packages for eddy covariance (EC) measurements have been developed for unoccupied aerial vehicles (UAVs) to measure the turbulent fluxes of latent heat (LE), sensible heat (H), and CO₂ (F_c) in the atmospheric boundary layer. This study aims to evaluate the performance of this UAV-based EC system. First, the measurement precision (1σ) of georeferenced wind was estimated to be 0.07 m s⁻¹. Then, the effect of the calibration parameter and aerodynamic characteristics of the UAV on wind measurement was examined by conducting a set of calibration flights. The results showed that the calibration improved the quality of the measured wind field, and the influence of upwash and the leverage effect can be ignored in wind measurement by the UAV. Third, for the measurements of turbulent fluxes, the error caused by instrumental noise was estimated to be 0.03 $\mathrm{\mu }\mathrm{mol}{\mathrm{m}}^{-\mathrm{2}}{\mathrm{s}}^{-\mathrm{1}}$ for F_c, 0.02 W m⁻² for H, and 0.08 W m⁻² for LE. Fourth, data from the standard operational flights were used to assess the influence of resonance on the measurements and to test the sensitivity of the measurement under the variation (±30 %) in the calibration parameters around their optimum value. The results showed that the effect of resonance mainly affected the measurement of CO₂ (∼5 %). The pitch offset angle (ε_θ) significantly affected the measurement of vertical wind (∼30 %) and turbulent fluxes (∼15 %). The heading offset angle (ε_ψ) mainly affected the measurement of horizontal wind (∼15 %), and other calibration parameters had no significant effect on the measurements. The results lend confidence to the use of the UAV-based EC system and suggest future improvements for the optimization of the next-generation system.

Land-use changes have profound effects on both socio-economic development and the environment. As a result, to optimize land-use planning and management, models are often employed to identify land-use patterns and their associated driving forces. In this work, physical and socioeconomic factors within the Yangtze River Delta Urban Agglomeration (YRDUA) from 2000 to 2015 were identified, integrated, and used as the foundation for a CLUMondo model. Subsequently, the Markov model and the CLUMondo model were combined to predict land-use changes in 2035. Natural growth (NG), economic development (ED), ecological protection (EP), and coordinated social and economic development (CSE) scenarios were set according to the land-use date in the assessment. Results showed that: (1) From 2000 to 2015, urban land increased by 8139.5 km² (3.93%), and the paddy field decreased by 7315.8 km² (8.78%). The Kappa coefficient of the CLUMondo model was 0.86, indicating that this model can be used to predict the land-use changes of the YRDUA. (2) When this trend was used to simulate landscape patterns in 2035, the land-use structure and landscape patterns varied among the four simulated urban development scenarios. Specifically, urban land increased by 47.6% (NG), 39.6% (ED), 32.9% (EP), and 23.2% (CSE). The paddy field was still the primary landscape, with 35.85% NG, 36.95% ED, 37.01% EP, and 36.96% CSE. Furthermore, under all four scenarios, the landscape pattern tended to simplify and fragment, while connectivity and equilibrium diminished. The results provided herein are intended to elucidate the law of urban agglomeration development and aid in promoting urban sustainable development.