More Like this

1. Knowledge-Driven GeoAI: Integrating Spatial Knowledge into Multi-Scale Deep Learning for Mars Crater Detection

   https://doi.org/10.3390/rs13112116  

   Hsu, Chia-Yu; Li, Wenwen; Wang, Sizhe (June 2021, Remote Sensing)

   null (Ed.)

   This paper introduces a new GeoAI solution to support automated mapping of global craters on the Mars surface. Traditional crater detection algorithms suffer from the limitation of working only in a semiautomated or multi-stage manner, and most were developed to handle a specific dataset in a small subarea of Mars’ surface, hindering their transferability for global crater detection. As an alternative, we propose a GeoAI solution based on deep learning to tackle this problem effectively. Three innovative features are integrated into our object detection pipeline: (1) a feature pyramid network is leveraged to generate feature maps with rich semantics across multiple object scales; (2) prior geospatial knowledge based on the Hough transform is integrated to enable more accurate localization of potential craters; and (3) a scale-aware classifier is adopted to increase the prediction accuracy of both large and small crater instances. The results show that the proposed strategies bring a significant increase in crater detection performance than the popular Faster R-CNN model. The integration of geospatial domain knowledge into the data-driven analytics moves GeoAI research up to the next level to enable knowledge-driven GeoAI. This research can be applied to a wide variety of object detection and image analysis tasks. 

   more » « less
2. Multiscale Spatial Patterns in Giant Dike Swarms Identified Through Objective Feature Extraction

   https://doi.org/10.1029/2022GC010842  

   Kubo_Hutchison, A; Karlstrom, L; Mittal, T (September 2023, Geochemistry, Geophysics, Geosystems)

   Dike swarms are ubiquitous on terrestrial planets and represent the frozen remnants of magma transport networks. However, spatial complexity, protracted emplacement history, and uneven surface exposure typically make it difficult to quantify patterns in dike swarms on different scales. In this study, we address this challenge using the Hough transform (HT) to objectively link dissected dike segments and analyze multiscale spatial structure in dike swarms. We apply this method to swarms of three scales: the Spanish Peaks, USA; the Columbia River Flood Basalt Group (CRBG), USA; the Deccan Traps Flood Basalts, India. First, we cluster dike segments in HT space, recognizing prevalent linearly aligned structures that represent single dikes or dike packets, with lengths up to 10 −  30x the mapped mean segment length. Second, we identify colinear and radial dike segment mesoscale structures within each data set, using the HT to segment swarms into constituent spatial patterns. We show that for both the CRBG and Deccan Traps, a single radial or circumferential swarm does not well characterize the data. Instead, multiple and sometimes overlapping mesoscale linear and radial features are prevalent suggesting a complex history of crustal stresses. The HT can provide useful insights in a variety of geologic settings where many quasi‐linear features, at any scale, are superimposed spatially. 

   more » « less
3. Map of ecological sites and ecological states for pastures 1, 4, 14, and 15 on the Chihuahuan Desert Rangeland Research Center, New Mexico

   https://doi.org/10.6073/pasta/682d05ab0527759cce23189843dd569f  

   Burkett, Laura M; Bestelmeyer, Brandon T (January 2023, Environmental Data Initiative)

   This data package includes an ArcMap geodatabase for the Chihuahuan Desert Rangeland Research Center (CDRRC) pastures 1, 4, 14, and 15: one polygon feature class, one point feature class, associated attribute tables and metadata. The spatial data, CDRRC1_4_14_15_StateMap_v1.gdb.zip, represents the ecological sites and states on Pastures 1, 4, 14 and 15 on the Chihuahuan Desert Rangeland Research Center, and includes field traverse data. CDRRC1_4_14_15_StateMapMetadata.pdf and TraversePointsMetadata.pdf contain the geospatial metadata provided by ArcMap. CDRRC1_4_14_15_StateMap_v1.csv is the attribute table associated with the state map’s polygon feature class, and TraversePoints.xlsx is the attribute table associated with the traverse points feature class and includes a sheet containing detailed attribute metadata. 

   more » « less
4. geodl: An R package for geospatial deep learning semantic segmentation using torch and terra

   https://doi.org/10.1371/journal.pone.0315127  

   Maxwell, Aaron E; Farhadpour, Sarah; Das, Srinjoy; Yang, Yalin (December 2024, PLOS ONE)

   Sun, Xiaoyong (Ed.)

   Convolutional neural network (CNN)-based deep learning (DL) methods have transformed the analysis of geospatial, Earth observation, and geophysical data due to their ability to model spatial context information at multiple scales. Such methods are especially applicable to pixel-level classification or semantic segmentation tasks. A variety of R packages have been developed for processing and analyzing geospatial data. However, there are currently no packages available for implementing geospatial DL in the R language and data science environment. This paper introduces the geodl R package, which supports pixel-level classification applied to a wide range of geospatial or Earth science data that can be represented as multidimensional arrays where each channel or band holds a predictor variable. geodl is built on the torch package, which supports the implementation of DL using the R and C++ languages without the need for installing a Python/PyTorch environment. This greatly simplifies the software environment needed to implement DL in R. Using geodl, geospatial raster-based data with varying numbers of bands, spatial resolutions, and coordinate reference systems are read and processed using the terra package, which makes use of C++ and allows for processing raster grids that are too large to fit into memory. Training loops are implemented with the luz package. The geodl package provides utility functions for creating raster masks or labels from vector-based geospatial data and image chips and associated masks from larger files and extents. It also defines a torch dataset subclass for geospatial data for use with torch dataloaders. UNet-based models are provided with a variety of optional ancillary modules or modifications. Common assessment metrics (i.e., overall accuracy, class-level recalls or producer’s accuracies, class-level precisions or user’s accuracies, and class-level F1-scores) are implemented along with a modified version of the unified focal loss framework, which allows for defining a variety of loss metrics using one consistent implementation and set of hyperparameters. Users can assess models using standard geospatial and remote sensing metrics and methods and use trained models to predict to large spatial extents. This paper introduces the geodl workflow, design philosophy, and goals for future development. 

   more » « less
5. An interpretable Bayesian clustering approach with feature selection for analyzing spatially resolved transcriptomics data

   https://doi.org/10.1093/biomtc/ujae066  

   Li, Huimin; Zhu, Bencong; Jiang, Xi; Guo, Lei; Xie, Yang; Xu, Lin; Li, Qiwei (July 2024, Biometrics)

   ABSTRACT Recent breakthroughs in spatially resolved transcriptomics (SRT) technologies have enabled comprehensive molecular characterization at the spot or cellular level while preserving spatial information. Cells are the fundamental building blocks of tissues, organized into distinct yet connected components. Although many non-spatial and spatial clustering approaches have been used to partition the entire region into mutually exclusive spatial domains based on the SRT high-dimensional molecular profile, most require an ad hoc selection of less interpretable dimensional-reduction techniques. To overcome this challenge, we propose a zero-inflated negative binomial mixture model to cluster spots or cells based on their molecular profiles. To increase interpretability, we employ a feature selection mechanism to provide a low-dimensional summary of the SRT molecular profile in terms of discriminating genes that shed light on the clustering result. We further incorporate the SRT geospatial profile via a Markov random field prior. We demonstrate how this joint modeling strategy improves clustering accuracy, compared with alternative state-of-the-art approaches, through simulation studies and 3 real data applications. 

   more » « less