Classifying bare earth (ground) points from Light Detection and Ranging (LiDAR) point clouds is well-established research in the forestry, topography, and urban domains using point clouds acquired by Airborne LiDAR System (ALS) at average point densities (≈2 points per meter-square (pts/m²)). The paradigm of point cloud collection has shifted with the advent of unmanned aerial systems (UAS) onboard affordable laser scanners with commercial utility (e.g., DJI Zenmuse L1 sensor) and unprecedented repeatability of UAS-LiDAR surveys. Therefore, there is an immediate need to investigate the existing methods, and to develop new ground classification methods, using UAS-LiDAR. In this paper, for the first time, traditional ground classification algorithms and modern machine learning methods were investigated to filter ground from point clouds of high-density UAS-LiDAR data (≈900 pts/m²) over five agricultural fields in North Dakota, USA. To this end, we tested frequently used ground classification algorithms: Cloth Simulation Function (CSF), Progressive Morphological Filter (PMF), Multiscale Curvature Classification (MCC), and ArcGIS ground classification algorithms along with the PointCNN deep learning model were trained. We investigated two aspects of ground classification algorithms and PointCNN: (a) Classification accuracy of optimized ground classification algorithms (i.e., fine adjustment is user-defined parameters) and PointCNN over training site, and (b) transferability potential over four yet diverse test agricultural fields. The well-established evaluation metrics of omission error, commission error, and total error, along with kappa coefficients showed that deep learning outperforms the traditional ground classification algorithms in both aspects: (a) overall classification accuracy, and (b) transferability over diverse agricultural fields.

Automated feature extraction from drone-based image point clouds (DIPC) is of paramount importance in precision agriculture (PA). PA is blessed with mechanized row seedlings to attain maximum yield and best management practices. Therefore, automated plantation rows extraction is essential in crop harvesting, pest management, and plant grow-rate predictions. Most of the existing research is consists on red, green, and blue (RGB) image-based solutions to extract plantation rows with the minimal background noise of test study sites. DIPC-based DSM row extraction solutions have not been tested frequently. In this research work, an automated method is designed to extract plantation row from DIPC-based DSM. The chosen plantation compartments have three different levels of background noise in UAVs images, therefore, methodology was tested under different background noises. The extraction results were quantified in terms of completeness, correctness, quality, and F1-score values. The case study revealed the potential of DIPC-based solution to extraction the plantation rows with an F1-score value of 0.94 for a plantation compartment with minimal background noises, 0.91 value for a highly noised compartment, and 0.85 for a compartment where DIPC was compromised. The evaluation suggests that DSM-based solutions are robust as compared to RGB image-based solutions to extract plantation-rows. Additionally, DSM-based solutions can be further extended to assess the plantation rows surface deformation caused by humans and machines and state-of-the-art is redefined.

Maturity is an important trait in dry pea breeding programs, but the conventional process predominately used to measure this trait can be time-consuming, labor-intensive, and prone to errors. Therefore, a more efficient and accurate approach would be desirable to support dry pea breeding programs. This study presents a novel approach for measuring dry pea maturity using machine learning algorithms and unmanned aerial systems (UASs)-collected data. We evaluated the abilities of five machine learning algorithms (random forest, artificial neural network, support vector machine, K-nearest neighbor, and naïve Bayes) to accurately predict dry pea maturity on field plots. The machine learning algorithms considered a range of variables, including crop height metrics, narrow spectral bands, and 18 distinct color and spectral vegetation indices. Backward feature elimination was used to select the most important features by iteratively removing insignificant ones until the model’s predictive performance was optimized. The study’s findings reveal that the most effective approach for assessing dry pea maturity involved a combination of narrow spectral bands, red-edge, near-infrared (NIR), and RGB-based vegetation indices, along with image textural metrics and crop height metrics. The implementation of a random forest model further enhanced the accuracy of the results, exhibiting the highest level of accuracy with a 0.99 value for all three metrics precision, recall, and f1 scores. The sensitivity analysis revealed that spectral features outperformed structural features when predicting pea maturity. While multispectral cameras achieved the highest accuracy, the use of RGB cameras may still result in relatively high accuracy, making them a practical option for use in scenarios where cost is a limiting factor. In summary, this study demonstrated the effectiveness of coupling machine learning algorithms, UASs-borne LIDAR, and multispectral data to accurately assess maturity in peas.

Climate change and Land-Use Land-Cover change (LULC) has significantly displaced the local rainfall patterns and weather conditions in Pakistan. This has resulted in a different climate-related problem, particularly vector borne diseases. Dengue transmission has emerged as one of the most devastating and life threatening disease in Pakistan, causing hundreds of deaths since its first outbreak. This study is designed to understand and analyze the disease patterns across two distinct study regions, using Geographic Information System (GIS), Satellite Remote Sensing (RS) along with climate and socio-economic and demographics datasets. The datasets have been analyzed by using GIS statistical analysis techniques. As a result, maps, tables and graphs have been plotted to estimate the most significant parameters. These parameters have been assigned a contribution weight value to prepare a model and Threat Index Map (TIM) for the study areas. Finally, the model has been tested and verified against existing datasets for both study areas. This model can be used as a disease Early Warning System (EWS).

Satellites are launched frequently to monitor the Earth’s dynamic surface processes. For example, the Landsat legacy has thrived for the past 50 years, spanning almost the entire application spectrum of Earth Sciences. On the other hand, fewer satellites are launched with a single specific mission to address pressing scientific questions, e.g., the study of polar icecaps and their response to climate change using Ice Cloud and the Land Elevation Satellite (ICESat) program with ICESat-1 (decommissioned in 2009) and ICESat-2. ICESat-2 has been operational since 2018 and has provided unprecedented success in space-borne LiDAR technology. ICESat-2 provides exceptional details of topographies covering inland ice, snow, glaciers, land, inland waterbodies, and vegetation in three-dimensional (3D) space and time, offering the unique opportunity to quantify the Earth’s surface processes. Nevertheless, ICESat-2 is not well known to some other disciplines, e.g., Geology and Geomorphology. This study, for the first time, introduces the use of ICESat-2 in aeolian sand dune studies, purely from an ICESat-2 remote sensing data perspective. Two objectives are investigated. first, a simplified approach to understanding ICESat-2 data products along with their application domains. Additionally, data processing methods and software applications are briefly explained to unify the information in a single article. Secondly, the exemplified use of ICESat-2 data in aeolian sand dune environments is analyzed compared to global Digital Elevation Models (DEMs), e.g., Shuttle Radar Topography Mission (SRTM). Our investigation shows that ICESat-2 provides high-resolution topographic details in desert environments with significant improvements to the existing methods, thereby facilitating geological education and field mapping. Aeolian sand dune environments can be better understood, at present, using ICESat-2 data compared to traditional DEM-based methods.

Wide-area drainage structure (DS) mapping is of great concern, as many DSs are reaching the end of their design life and information on their location is usually absent. Recently, airborne laser scanning (ALS) has been proven useful for DS mapping through manual methods using ALS-derived digital elevation models (DEMs) and hillshade images. However, manual methods are slow and labor-intensive. To overcome these limitations, this paper proposes an automated DS mapping algorithm (DSMA) using classified ALS point clouds and road centerline information. The DSMA begins with removing ALS ground points within the buffer of the road centerlines; the size of the buffer varies according to different road classes. An ALS-modified DEM (ALS-mDEM) is then generated from the remaining ground points. A drainage network (DN) is derived from the ALS-mDEM. Candidate DSs are then obtained by intersecting the DN with the road centerlines. Finally, a refinement buffer of 15 m is placed around each candidate DS to prevent duplicate DS from being generated in close proximity. A total area of 50 km², including an urban site and a rural site, in Vermont, USA, was used to assess the DSMA. Based on the road functional classification scheme of the Federal Highway Administration (FHWA), the centerline information regarding FHWA roads was obtained from a public data portal. The centerline information on non-FHWA roads, i.e., private roads and streets, was derived from the impervious surface data of a land cover dataset. A benchmark DS dataset was gathered from the transport agency of Vermont and was further augmented using Google Earth Street View images by the authors. The one-to-one correspondence between the benchmark DS and mapped DS for these two sites was then established. The positional accuracy was assessed by computing the Euclidian distance between the benchmark DS and mapped DS. The mean positional accuracy for the urban site and rural site were 13.5 m and 15.8 m, respectively. F1-scores were calculated to assess the prediction accuracy. For FHWA roads, the F1-scores were 0.87 and 0.94 for the urban site and rural site, respectively. For non-FHWA roads, the F1-scores were 0.72 and 0.74 for the urban site and rural site, respectively.