The mineral composition of lunar regolith influences brightness temperature (TB) as observed by the microwave radiometer (MRM); however, the large-scale spatial relationship between TB and mineral abundance has yet to be sufficiently revealed. This study aims to quantify the impact of specific mineral abundances (plagioclase and ilmenite) on TB distribution, using MRM 37-GHz data from Chang’E-2 and mineral abundance products from Kaguya. We applied hour angle correction and latitude normalization to produce high-accuracy TB maps and developed a self-adaptive moving-window method to remove strip noise to produce higher precision mineral abundance maps. Using these two types of maps, we performed comprehensive large-scale spatial analysis of TB and mineral abundance using a bivariate spatial autocorrelation model and a geographically weighted regression (GWR) approach considering spatial similarity and heterogeneity, respectively. The bivariate analysis indicates a negative spatial correlation between TB and plagioclase abundance, while a positive spatial correlation between TB and ilmenite abundance. In addition, bivariate anomalies, including both hot and cold spots of diurnal TB amplitude (i.e., noon minus nighttime), were identified through the simultaneous consideration of TB and mineral abundance. The GWR analysis reveals regional variations in the impact of mineral abundances on diurnal TB amplitudes. These correlations can be attributed to the spatial distributions and variations in TB, which arise from the unique dielectric and thermal properties of minerals across distinct regions on the Moon. These findings contribute to a better understanding of subsurface thermal behavior and regimes, enhancing our comprehension of lunar evolution.

Accurate simulation of subsurface physical temperatures in lunar south polar craters is essential for thermal environment analysis in landing site selection. In this study, we developed an improved method for simulating large-scale subsurface temperature by integrating multi-source datasets, including Lunar Reconnaissance Orbiter (LRO) DEM, LRO Diviner infrared brightness temperature (TB), and Chang’E-2 microwave TB. The proposed method accounts for differences in heat sources between non-permanently shaded regions (non-PSR) and permanently shaded regions (PSR) craters, applying effective solar irradiance with terrain effect for non-PSR craters, and calibrated infrared TB with emissivity effect for PSR craters. Additionally, we incorporated key model parameters, including an annual model period and updated thermal conductivity, into a one-dimensional (1-D) heat transfer model. This method was applied to simulate subsurface temperatures (0–2 m depth) in lunar south polar craters, validated by the microwave radiative transfer model and observed microwave TB data. The simulation results indicate that temperatures near the lunar south polar are generally lower than those in the 80°-85°S latitude range. These temperature profiles can be applied to quantitatively estimate the detection depths of heat flow and buried water ice. Furthermore, the model period considering seasonality shows a stronger impact on temperature simulations than other model parameters — altering temperatures by 20–40 K in non-PSR and by 20–30 K in PSR. Our method and findings provide valuable insights for future scientific exploration of the lunar south pole region and contribute to a better understanding of subsurface thermal evolution.

Digital elevation models (DEMs) play a crucial role in scientific research and exploration mission of the lunar south pole regions, as they offer vital topographic and morphological information of terrain surfaces. Surface points processed from various remote sensors provide a discrete but accurate measurements of lunar terrains. However, reconstructing high-resolution terrains from surface points poses significant challenges for neural networks primarily due to the lack of grid connectivity inherent in unordered surface points. Therefore, this study develops a point-based terrain reconstruction framework that incorporates learnable neural shape priors to better capture complex terrain geometry. To model structural characteristics inherent in three-dimensional (3-D) surface points, signed distance field (SDF) is introduced as a continuous representation of lunar surfaces. Moreover, we train a 3-D point-based encoder–decoder network that allows terrain modeling from unstructured surface points with encoded planar features. Additionally, a dynamic planar features strategy is proposed to optimize the framework’s performance to the characteristics of terrain flatness. Experiments were conducted on photoclinometry DEMs of the lunar polar region to demonstrate the advantages of our proposed framework. The qualitative and quantitative results highlight that our framework reconstructs accurate terrain geometry, outperforming traditional methods in terms of elevation, slope, aspect and roughness. Furthermore, the model exhibits a generalization ability when applied to both Lunar Orbiter Laser Altimeter (LOLA) measurements and unseen regions, underscoring its effectiveness in lunar exploration tasks.

The accurate matching of planetary remote sensing images (PRSIs) is the premise of accurate planetary terrain mapping. However, PRSIs often lack apparent man-made structures such as buildings or roads, leading to difficulties in feature description. In addition, the PRSIs collected by different sensors are affected by the imaging mechanism and the solar illumination, and there are obvious nonlinear radiation differences (NRDs). These problems make the matching of PRSIs difficult. To address the above issues, this article proposes a PRSI matching method based on optimized bandpass filtering and local topological prior, divided into two stages: coarse matching and fine matching. In the coarse matching stage, we first use the bandpass filtering to calculate the phase congruency (PC). Then, the feature block descriptors are constructed, and the local topology consensus is used to achieve the coarse alignment of feature blocks. Finally, we extract the point features and use the matching results of block features to narrow the matching range of point features. Based on the coarse matching results, the precision and reliability of the results are further improved through fine matching. The experimental results achieved with a PRSI dataset with 75 image pairs demonstrate that our method is superior to other recent methods, the matching accuracy of the proposed method is improved by more than 2.367 pixels, and the success rate is improved by over 22.667%. The source code will be publicly available athttps://github.com/WGY-RS/OFLP.

The Martian surface landforms are highly related to the safe landing and traversability of Mars rovers. Furthermore, landforms associated with the presence of water/ice, minerals and biosignatures can provide valuable insights for Mars exploration missions, particularly in relation to the selection of landing or sample collection sites. The small number of Martian landform datasets and the scarcity of labelable landform samples over Mars make the precise mapping of Martian landforms a challenging task. In this article, we propose a stepwise deep feature transfer (SDFT) model for the mapping of Martian landforms with a small number of labeled samples. The SDFT model comprises two transfer steps. In the first transfer step, a deep learning model trained on a large public source dataset from Earth is transferred to a medium sized public dataset from Mars. This transfer is conducted through a standard pre-training and fine-tuning procedure utilizing a linear classifier. In the second transfer step, the model is further transferred to a small number of target datasets on Mars through a pre-training and fine-tuning procedure with a cosine distance classifier. The stepwise training technique mitigates the challenges associated with varying datasets and small training samples. The proposed SDFT model has been validated on two self-built sample sets using images from the Mars Reconnaissance Orbiter’s Context Camera (CTX). It has also been employed for landform mapping in two local regions with small samples to evaluate its effectiveness in comparison with existing state-of-the-art methods.

In this letter, wavelet synchrosqueezing transformation (WSST)-based technique is introduced for ground penetrating radar (GPR) near-surface void recognition. WSST can extract the signal features effectively because the ground surface reflection or antenna coupling suppresses the target echo. However, these features are distorted by mathematical procedures and clutter. A shallow neural network (SNN) is applied to estimate the possible targets in this case. The SNN only has full connection layers, and its training sets are simulated data under different levels of SNR. After the network is trained, the result scalar can be used to identify the near-surface targets. Simulation and experimental results show that the proposed method achieves 1/10 range resolution binary classification. Compared with recent studies, the detectable thickness improves (at least two times smaller). Besides, the method has a limited-size network and can be trained in situ, which makes it more suitable for engineering uses.

The positioning accuracy of synthetic aperture radar (SAR) images is affected by factors, such as satellite platform instability, aging of on-board instruments, and environmental changes. Geometric calibration is a commonly employed and cost-effective method to enhance the positioning accuracy of SAR images. The classical point-based geometric calibration (PB-GC) model, however, only utilizes the location of ground control points (GCPs) and does not fully exploit the spatial relationships among the GCPs. This study introduces a high-precision geometric calibration method that builds upon the classical model for calibrating SAR imaging systems. This method incorporates the Co-Line-GC and Co-Circle-GC models, where the former uses GCPs distributed on a line while the latter uses GCPs distributed on a circle. The results reveal that, compared to the classical model, our approach enhances the positioning accuracy of Gaofen-3 and Sentinel-1A SAR images by approximately 2 m in eastern China, achieving a mean positioning accuracy of 3.02 m. In terms of calibration performance, a comparison between postcalibrated and precalibrated images indicates that the images are shifted, not distorted, and a better match of the same features between different scenes in the image mosaic is observed after calibration. The improved positioning accuracy of SAR images significantly contributes to global remote sensing mapping, land use change monitoring, and ground target detection applications.

For urban growth modeling, assessment metrics derived from cell-by-cell comparisons are mainly related to the size of the study area and the urban growth rate. Non-urban areas always occupy an important part of the city to which cellular automata (CA) models do not contribute much, so the simulation accuracy is often exaggerated when this part is included. To enable comparing simulation results across models, regions, and time, we developed an improved equivalent area-based assessment (EQASS) method using cell-by-cell comparison metrics. As against existing assessment methods, EQASS is computed by including the same area of urban and suburban areas (i.e., equivalent areas). EQASS was tested in three Chinese coastal cities using a heuristic CA model and two spatial statistical CA models to simulate urban growth. The results show that EQASS can exclude correct rejections that are not attributable to CA models; these correct rejections have a significant impact on the model assessment. The improved assessment can better evaluate the performance of CA models across regions and over time than the conventional assessment method that accounts for the full study area. This study extends the simulation assessment method and provides a good solution for selecting the best CA model from many candidate models.

Accurate detection of the multiple classes in aerial images has become possible with the use of anchor-based object detectors. However, anchor-based object detectors place a large number of preset anchors on images and regress the target bounding box while anchor-free object detections predict the location of objects directly and avoid the carefully predefined anchor box parameters. Object detection in aerial images is faced with two main challenges: 1) the scale diversity of the geospatial objects; and 2) the cluttered background in complex scenes. In this letter, to address these challenges, we present a novel Anchor-Free Network with a Density map and attention mechanism (DA2FNet). Considering the extreme density variations of the detection instances among the different categories in aerial images, the proposed DA2FNet model conducts density map estimation with image-level supervision for the geospatial object counting, to acquire global knowledge about the scale information. A simple and effective image-level global counting loss function is also introduced. In addition, a compositional attention network is further introduced to enhance the saliency of the foreground objects. The proposed DA2FNet method was compared with the state-of-the-art object detection models, achieving excellent performance on the NWPU VHR-10, RSOD, and DOTA datasets.

Array interferometric synthetic aperture radar (Array InSAR) has a 3-D resolution capability and solves the layover problem in interferometric SAR (InSAR) by arranging multiple antennas in the cross-orbit direction. Airborne Array InSAR point clouds are obtained from two scans for complete building information in urban areas, resulting in very low overlapping point cloud. The existing methods are difficult to extract the identical features for the registration of Array InSAR point clouds. To this end, a robust registration approach Array InSAR point clouds in urban areas is proposed in this study. The main contribution of this article is raising the theoretically optimal transformation for achieving point cloud registration, considering the constraint from parallel facades of a certain building. Point density estimation is adopted to retain building facade points for initial registration. The facade pairs of a specific building are then matched and divided into two categories by judging whether one contains the concave–convex features or not, for performing rotation rectification and fine shift fixation, respectively. Experimental results of both simulated and real data validate the feasibility and reliability of our approach. For the simulated data, the results reach an average rotation error of about 0.01° and an average translation error of less than 0.8 m. For the real data, two evaluation criteria are designed for the lack of reference data. The results reach an average of 0.4° of the defined angle difference and less 0.8-m distance difference from the source facades center to the normal extension of the target facades.

We develop a new geographical cellular automata (CA) modeling framework, named UrbanCA, through reconstructing the essential CA structure and incorporating nonspatial, spatial, and heuristic approaches. The new UrbanCA is featured by 1) the improvement of the CA modeling framework by reformulating relationships among CA components, 2) the development of two scaling parameters to adjust the effects of transition probability and neighborhood, 3) the incorporation of a variety of statistical and heuristic methods to construct transition rules, and 4) the inclusion of urban planning regulations and spatial heterogeneities to project future urban scenarios. To illustrate the effectiveness of UrbanCA, we calibrate a CA model using artificial bee colony (ABC) to simulate the past urban patterns and predict future scenarios in Shanghai of China. The results show that UrbanCA under different scaling parameters is comparable to CA-Markov (as a reference model) concerning the accuracy of the end-state and change simulations, and is better than CA-Markov regarding the driving factor’s ability to explain the modeling outcomes. UrbanCA provides more choices compared to existing CA software packages, and the models are readily calibrated elsewhere to simulate the dynamic urban growth and assess the resulting natural and socioeconomic impacts.

Cellular automata (CA) models are in growing use for land-use change simulation and future scenario prediction. It is necessary to conduct model assessment that reports the quality of simulation results and how well the models reproduce reliable spatial patterns. Here, we review 347 CA articles published during 1999–2018 identified by a Scholar Google search using ‘cellular automata’, ‘land’ and ‘urban’ as keywords. Our review demonstrates that, during the past two decades, 89% of the publications include model assessment related to dataset, procedure and result using more than ten different methods. Among all methods, cell-by-cell comparison and landscape analysis were most frequently applied in the CA model assessment; specifically, overall accuracy and standard Kappa coefficient respectively rank first and second among all metrics. The end-state assessment is often criticized by modelers because it cannot adequately reflect the modeling ability of CA models. We provide five suggestions to the method selection, aiming to offer a background framework for future method choices as well as urging to focus on the assessment of input data and error propagation, procedure, quantitative and spatial change, and the impact of driving factors.

A novel generalized pattern search GPS-based cellular automata GPS-CA model was developed to simulate urban land-use change in a GIS environment. The model is built on a fitness function that computes the difference between the observed results produced from remote-sensing images and the simulated results produced by a general CA model. GPS optimization incorporating genetic algorithms GAs searches for the minimum difference, i.e. the smallest accumulated residuals, in fitting the CA transition rules. The CA coefficients captured by the GPS method have clear physical meanings that are closely associated with the dynamic mechanisms of land-use change. The GPS-CA model was applied to simulate urban land-use change in Kunshan City in the Yangtze River Delta from 2000 to 2015. The results show that the GPS method had a smaller root mean squared error 0.2821 than a logistic regression LR method 0.5256 in fitting the CA transition rules. The GPS-CA model thus outperformed the LR-CA model, with an overall accuracy improvement of 4.7%. As a result, the GPS-CA model should be a superior tool for modeling land-use change as well as predicting future scenarios in response to different conditions to support the sustainable urban development.

This article presents a novel cellular automata (CA) approach to simulate the spatio-temporal process of urban land-use change based on the simulated annealing (SA) algorithm. The SA algorithm enables dynamic optimisation of the CA's transition rules that would otherwise be difficult to configure using conventional mathematical methods. In this heuristic approach, an objective function is constructed based on a theoretical accumulative disagreement between the simulated land-use pattern and the actual land-use pattern derived from remotely sensed imagery. The function value that measures the mismatch between the actual and the simulated land-use patterns would be minimised randomly through the SA process. Hence, a set of attribution parameters that can be used in the CA model is achieved. An SA optimisation tool was developed using Matlab and incorporated into the cellular simulation in GIS to form an integrated SACA model. An application of the SACA model to simulate the spatio-temporal process of land-use change in Jinshan District of Shanghai Municipality, PR China, from 1992 to 2008 shows that this modelling approach is efficient and robust and can be used to reconstruct historical urban land-use patterns to assist with urban planning policy-making and actions. Comparison of the SACA model with a typical CA model based on a logistic regression method without the SA optimisation (also known as LogCA) shows that the SACA model generates better simulation results than the LogCA model, and the improvement of the SACA over the LogCA model is largely attributed to higher locational accuracy, a feature desirable in most spatially explicit simulations of geographical processes.