Data assimilation plays a dual role in advancing the “scientific” understanding and serving as an “engineering tool” for the Earth system sciences. Land data assimilation (LDA) has evolved into a distinct discipline within geophysics, facilitating the harmonization of theory and data and allowing land models and observations to complement and constrain each other. Over recent decades, substantial progress has been made in the theory, methodology, and application of LDA, necessitating a holistic and in‐depth exploration of its full spectrum. Here, we present a thorough review elucidating the theoretical and methodological developments in LDA and its distinctive features. This encompasses breakthroughs in addressing strong nonlinearities in land surface processes, exploring the potential of machine learning approaches in data assimilation, quantifying uncertainties arising from multiscale spatial correlation, and simultaneously estimating model states and parameters. LDA has proven successful in enhancing the understanding and prediction of various land surface processes (including soil moisture, snow, evapotranspiration, streamflow, groundwater, irrigation and land surface temperature), particularly within the realms of water and energy cycles. This review outlines the development of global, regional, and catchment‐scale LDA systems and software platforms, proposing grand challenges of generating land reanalysis and advancing coupled land‒atmosphere DA. We lastly highlight the opportunities to expand the applications of LDA from pure geophysical systems to coupled natural and human systems by ingesting a deluge of Earth observation and social sensing data. The paper synthesizes current LDA knowledge and provides a steppingstone for its future development, particularly in promoting dual driven theory‐data land processes studies.

Understanding the spatial distribution of populations at a finer spatial scale has important value for many applications, such as disaster risk rescue operations, business decision-making, and regional planning. In this study, a random forest (RF)-based population density mapping method was proposed in order to generate high-precision population density data with a 100 m × 100 m grid in mainland China in 2015 (hereafter referred to as ‘Popi’). Besides the commonly used elevation, slope, Normalized Vegetation Index (NDVI), land use/land cover, roads, and National Polar Orbiting Partnership/Visible Infrared Imaging Radiometer Suite (NPP/VIIRS), 16,101,762 records of points of interest (POIs) and 2867 county-level censuses were used in order to develop the model. Furthermore, 28,505 township-level censuses (74% of the total number of townships) were collected in order to evaluate the accuracy of the Popi product. The results showed that the utilization of multi-source data (especially the combination of POIs and NPP/VIIRS data) can effectively improve the accuracy of population mapping at a finer scale. The feature importances of the POIs and NPP/VIIRS are 0.49 and 0.14, respectively, which are higher values than those obtained for other natural factors. Compared with the Worldpop population dataset, the Popi data exhibited a higher accuracy. The number of accurately-estimated townships was 19,300 (67.7%) in the Popi product and 16,237 (56.9%) in the Worldpop product. The Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE) were 14,839 and 7218, respectively, for Popi, and 18,014 and 8572, respectively, for Worldpop. The research method in this paper could provide a reference for the spatialization of other socioeconomic data (such as GDP).

Cloud obscuration leaves significant gaps in MODIS snow cover products. In this study, an innovative gap-filling method based on the concept of non-local spatio-temporal filtering (NSTF) is proposed to reconstruct the cloud gaps in MODIS fractional snow cover (SCF) products. The ground information of a gap pixel was estimated by using the appropriate similar pixels in the remaining known part of an image via an automatic machine learning technique. We take the MODIS SCF product cloud gap filling data from 2001 to 2016 in Northern Xinjiang, China as an example. The results demonstrate that the methodology can generate almost continuous spatio-temporal, daily MODIS SCF images, and it leaves only 0.52% of cloud gaps long-term, on average. The validation results based on “cloud assumption” exhibit high accuracy, with a higher $R^2$ exceeding 0.8, a lower RMSE of 0.1, an overestimated error of 1.13%, an underestimated error of 1.4%, and a spatial efficiency (SPAEF) of 0.78. The validation based on 50 in situ snow depth observations demonstrates the superiority of the methodology in terms of accuracy and consistency. The overall accuracy is 93.72%. The average omission and commission error have increased approximately 1.16 and 0.53% compared with the original MODIS SCF products under a clear sky term.

Accurate estimation of crop area is essential to adjusting the regional crop planting structure and the rational planning of water resources. However, it is quite challenging to map crops accurately by high-resolution remote sensing images because of the ecological gradient and ecological convergence between crops and non-crops. The purpose of this study is to explore the combining application of high-resolution multi-temporal Sentinel-1 (S1) radar backscatter and Sentinel-2 (S2) optical reflectance images for maize mapping in highly complex and heterogeneous landscapes in the middle reaches of Heihe River, northwest China. We proposed a new two-step method of vegetation extraction and followed by maize extraction, that is, extract the vegetation-covered areas first to reduce the inter-class variance by using a Random Forest (RF) classifier based on S2 data, and then extract the maize distribution in the vegetation area by using another RF classifier based on S1 and/or S2 data. The results demonstrate that the vegetation extraction classifier successfully identified vegetation-covered regions with an overall accuracy above 96% in the study area, and the accuracy of the maize extraction classifier constructed by the combined multi-temporal S1 and S2 images is significantly improved compared with that S1 (alone) or S2 (alone), with an overall accuracy of 87.63%, F1_Score of 0.86, and Kappa coefficient of 0.75. In addition, with the introduction of multi-temporal S1 and/or S2 images in crop growing season, the constructed RF model is more beneficial to maize mapping.

Accurate high-resolution gridded livestock distribution data are of great significance for the rational utilization of grassland resources, environmental impact assessment, and the sustainable development of animal husbandry. Traditional livestock distribution data are collected at the administrative unit level, which does not provide a sufficiently detailed geographical description of livestock distribution. In this study, we proposed a scheme by integrating high-resolution gridded geographic data and livestock statistics through machine learning regression models to spatially disaggregate the livestock statistics data into 1 km × 1 km spatial resolution. Three machine learning models, including support vector machine (SVM), random forest (RF), and deep neural network (DNN), were constructed to represent the complex nonlinear relationship between various environmental factors (e.g., land use practice, topography, climate, and socioeconomic factors) and livestock density. By applying the proposed method, we generated a set of 1 km × 1 km spatial distribution maps of cattle and sheep for western China from 2000 to 2015 at five-year intervals. Our projected cattle and sheep distribution maps reveal the spatial heterogeneity structures and change trend of livestock distribution at the grid level from 2000 to 2015. Compared with the traditional census livestock density, the gridded livestock distribution based on DNN has the highest accuracy, with the determinant coefficient (R²) of 0.75, root mean square error (RMSE) of 9.82 heads/km² for cattle, and the R² of 0.73, RMSE of 31.38 heads/km² for sheep. The accuracy of the RF is slightly lower than the DNN but higher than the SVM. The projection accuracy of the three machine learning models is superior to those of the published Gridded Livestock of the World (GLW) datasets. Consequently, deep learning has the potential to be an effective tool for high-resolution gridded livestock projection by combining geographic and census data.

Wildfires have a significant impact on the atmosphere, terrestrial ecosystems, and society. Real-time monitoring of wildfire locations is crucial in fighting wildfires and reducing human casualties and property damage. Geostationary satellites offer the advantage of high temporal resolution and are gradually being used for real-time fire detection. In this study, we constructed a fire label dataset using the stable VNP14IMG fire product and used the random forest (RF) model for fire detection based on Himawari-8 multiband data. The band calculation features related brightness temperature, spatial features, and auxiliary data as input used in this framework for model training. We also used a recursive feature elimination method to evaluate the impact of these features on model accuracy and to exclude redundant features. The daytime and nighttime RF models (RF-D/RF-N) are separately constructed to analyze their applicability. Finally, we extensively evaluated the model performance by comparing them with the Japan Aerospace Exploration Agency (JAXA) wildfire product. The RF models exhibited higher accuracy, with recall and precision rates of 95.62% and 59%, respectively, and the recall rate for small fires was 19.44% higher than that of the JAXA wildfire product. Adding band calculation features and spatial features, as well as feature selection, effectively reduced the overfitting and improved the model’s generalization ability. The RF-D model had higher fire detection accuracy than the RF-N model. Omission errors and commission errors were mainly concentrated in the adjacent pixels of the fire clusters. In conclusion, our VIIRS fire product and Himawari-8 data-based fire detection model can monitor the fire location in real time and has excellent detection capability for small fires, making it highly significant for fire detection.