An official website of the United States government
Abstract Many studies of Earth surface processes and landscape evolution rely on having accurate and extensive data sets of surficial geologic units and landforms. Automated extraction of geomorphic features using deep learning provides an objective way to consistently map landforms over large spatial extents. However, there is no consensus on the optimal input feature space for such analyses. We explore the impact of input feature space for extracting geomorphic features from land surface parameters (LSPs) derived from digital terrain models (DTMs) using convolutional neural network (CNN)‐based semantic segmentation deep learning. We compare four input feature space configurations: (a) a three‐layer composite consisting of a topographic position index (TPI) calculated using a 50 m radius circular window, square root of topographic slope, and TPI calculated using an annulus with a 2 m inner radius and 10 m outer radius, (b) a single illuminating position hillshade, (c) a multidirectional hillshade, and (d) a slopeshade. We test each feature space input using three deep learning algorithms and four use cases: two with natural features and two with anthropogenic features. The three‐layer composite generally provided lower overall losses for the training samples, a higher F1‐score for the withheld validation data, and better performance for generalizing to withheld testing data from a new geographic extent. Results suggest that CNN‐based deep learning for mapping geomorphic features or landforms from LSPs is sensitive to input feature space. Given the large number of LSPs that can be derived from DTM data and the variety of geomorphic mapping tasks that can be undertaken using CNN‐based methods, we argue that additional research focused on feature space considerations is needed and suggest future research directions. We also suggest that the three‐layer composite implemented here can offer better performance in comparison to using hillshades or other common terrain visualization surfaces and is, thus, worth considering for different mapping and feature extraction tasks.
more »
« less
Land-surface parameters for spatial predictive mapping and modeling
Land-surface parameters derived from digital land surface models (DLSMs) (for example, slope, surface curvature, topographic position, topographic roughness, aspect, heat load index, and topographic moisture index) can serve as key predictor variables in a wide variety of mapping and modeling tasks relating to geomorphic processes, landform delineation, ecological and habitat characterization, and geohazard, soil, wetland, and general thematic mapping and modeling. However, selecting features from the large number of potential derivatives that may be predictive for a specific feature or process can be complicated, and existing literature may offer contradictory or incomplete guidance. The availability of multiple data sources and the need to define moving window shapes, sizes, and cell weightings further complicate selecting and optimizing the feature space. This review focuses on the calculation and use of DLSM parameters for empirical spatial predictive modeling applications, which rely on training data and explanatory variables to make predictions of landscape features and processes over a defined geographic extent. The target audience for this review is researchers and analysts undertaking predictive modeling tasks that make use of the most widely used terrain variables. To outline best practices and highlight future research needs, we review a range of land-surface parameters relating to steepness, local relief, rugosity, slope orientation, solar insolation, and moisture and characterize their relationship to geomorphic processes. We then discuss important considerations when selecting such parameters for predictive mapping and modeling tasks to assist analysts in answering two critical questions: What landscape conditions or processes does a given measure characterize? How might a particular metric relate to the phenomenon or features being mapped, modeled, or studied? We recommend the use of landscape- and problem-specific pilot studies to answer, to the extent possible, these questions for potential features of interest in a mapping or modeling task. We describe existing techniques to reduce the size of the feature space using feature selection and feature reduction methods, assess the importance or contribution of specific metrics, and parameterize moving windows or characterize the landscape at varying scales using alternative methods while highlighting strengths, drawbacks, and knowledge gaps for specific techniques. Recent developments, such as explainable machine learning and convolutional neural network (CNN)-based deep learning, may guide and/or minimize the need for feature space engineering and ease the use of DLSMs in predictive modeling tasks.
more »
« less
- Award ID(s):
- 2046059
- PAR ID:
- 10329624
- Date Published:
- Journal Name:
- Earthscience reviews
- Volume:
- 226
- ISSN:
- 0012-8252
- Page Range / eLocation ID:
- 103944
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Semantic segmentation algorithms, such as UNet, that rely on convolutional neural network (CNN)-based architectures, due to their ability to capture local textures and spatial context, have shown promise for anthropogenic geomorphic feature extraction when using land surface parameters (LSPs) derived from digital terrain models (DTMs) as input predictor variables. However, the operationalization of these supervised classification methods is limited by a lack of large volumes of quality training data. This study explores the use of transfer learning, where information learned from another, and often much larger, dataset is used to potentially reduce the need for a large, problem-specific training dataset. Two anthropogenic geomorphic feature extraction problems are explored: the extraction of agricultural terraces and the mapping of surface coal mine reclamation-related valley fill faces. Light detection and ranging (LiDAR)-derived DTMs were used to generate LSPs. We developed custom transfer parameters by attempting to predict geomorphon-based landforms using a large dataset of digital terrain data provided by the United States Geological Survey’s 3D Elevation Program (3DEP). We also explored the use of pre-trained ImageNet parameters and initializing models using parameters learned from the other mapping task investigated. The geomorphon-based transfer learning resulted in the poorest performance while the ImageNet-based parameters generally improved performance in comparison to a random parameter initialization, even when the encoder was frozen or not trained. Transfer learning between the different geomorphic datasets offered minimal benefits. We suggest that pre-trained models developed using large, image-based datasets may be of value for anthropogenic geomorphic feature extraction from LSPs even given the data and task disparities. More specifically, ImageNet-based parameters should be considered as an initialization state for the encoder component of semantic segmentation architectures applied to anthropogenic geomorphic feature extraction even when using non-RGB image-based predictor variables, such as LSPs. The value of transfer learning between the different geomorphic mapping tasks may have been limited due to smaller sample sizes, which highlights the need for continued research in using unsupervised and semi-supervised learning methods, especially given the large volume of digital terrain data available, despite the lack of associated labels.more » « less
-
Increased access to high-resolution topography has revolutionized our ability to map out fine-scale topographic features at watershed to landscape scales. As our “vision” of the land surface has improved, so has the need for more robust quantification of the accuracy of the geomorphic maps we derive from these data. One broad class of mapping challenges is that of binary classification whereby remote sensing data are used to identify the presence or absence of a given feature. Fortunately, there is a large suite of metrics developed in the data sciences well suited to quantifying the pixel-level accuracy of binary classifiers. This analysis focuses on how these metrics perform when there is a need to quantify how the number and extent of landforms are expected to vary as a function of the environmental forcing (e.g., due to climate, ecology, material property, erosion rate). Results from a suite of synthetic surfaces show how the most widely used pixel-level accuracy metric, the F1 score, is particularly poorly suited to quantifying accuracy for this kind of application. Well-known biases to imbalanced data are exacerbated by methodological strategies that calibrate and validate classifiers across settings where feature abundances vary. The Matthews correlation coefficient largely removes this bias over a wide range of feature abundances such that the sensitivity of accuracy scores to geomorphic setting instead embeds information about the size and shape of features and the type of error. If error is random, the Matthews correlation coefficient is insensitive to feature size and shape, though preferential modification of the dominant class can limit the domain over which scores can be compared. If the error is systematic (e.g., due to co-registration error between remote sensing datasets), this metric shows strong sensitivity to feature size and shape such that smaller features with more complex boundaries induce more classification error. Future studies should build on this analysis by interrogating how pixel-level accuracy metrics respond to different kinds of feature distributions indicative of different types of surface processes.more » « less
-
Machine learning (ML) methods, such as artificial neural networks (ANN), k-nearest neighbors (kNN), random forests (RF), support vector machines (SVM), and boosted decision trees (DTs), may offer stronger predictive performance than more traditional, parametric methods, such as linear regression, multiple linear regression, and logistic regression (LR), for specific mapping and modeling tasks. However, this increased performance is often accompanied by increased model complexity and decreased interpretability, resulting in critiques of their “black box” nature, which highlights the need for algorithms that can offer both strong predictive performance and interpretability. This is especially true when the global model and predictions for specific data points need to be explainable in order for the model to be of use. Explainable boosting machines (EBM), an augmentation and refinement of generalize additive models (GAMs), has been proposed as an empirical modeling method that offers both interpretable results and strong predictive performance. The trained model can be graphically summarized as a set of functions relating each predictor variable to the dependent variable along with heat maps representing interactions between selected pairs of predictor variables. In this study, we assess EBMs for predicting the likelihood or probability of slope failure occurrence based on digital terrain characteristics in four separate Major Land Resource Areas (MLRAs) in the state of West Virginia, USA and compare the results to those obtained with LR, kNN, RF, and SVM. EBM provided predictive accuracies comparable to RF and SVM and better than LR and kNN. The generated functions and visualizations for each predictor variable and included interactions between pairs of predictor variables, estimation of variable importance based on average mean absolute scores, and provided scores for each predictor variable for new predictions add interpretability, but additional work is needed to quantify how these outputs may be impacted by variable correlation, inclusion of interaction terms, and large feature spaces. Further exploration of EBM is merited for geohazard mapping and modeling in particular and spatial predictive mapping and modeling in general, especially when the value or use of the resulting predictions would be greatly enhanced by improved interpretability globally and availability of prediction explanations at each cell or aggregating unit within the mapped or modeled extent.more » « less
-
Abstract Features of landscape morphology—including slope, curvature, and drainage dissection—are important controls on runoff generation in upland landscapes. Over long timescales, runoff plays an essential role in shaping these same features through surface erosion. This feedback between erosion and runoff generation suggests that modeling long‐term landscape evolution together with dynamic runoff generation could provide insight into hydrological function. Here we examine the emergence of variable source area runoff generation in a new coupled hydro‐geomorphic model that accounts for water balance partitioning between surface flow, subsurface flow, and evapotranspiration as landscapes evolve over millions of years. We derive a minimal set of dimensionless numbers that provide insight into how hydrologic and geomorphic parameters together affect landscapes. Across the parameter space we investigated, model results collapsed to a single inverse relationship between the dimensionless relief and the ratio of catchment quickflow to discharge. Furthermore, we found an inverse relationship between the Hillslope number, which describes topographic relief relative to aquifer thickness, and the proportion of the landscape that was variably saturated. While the model generally produces fluvial topography visually similar to simpler landscape evolution models, certain parameter combinations produce wide valley bottom wetlands and non‐dendritic, trellis‐like drainage networks, which may reflect real conditions in some landscapes where aquifer gradients become decoupled from topography. With these results, we demonstrate the power of hydro‐geomorphic models for generating new insights into hydrological processes, and also suggest that subsurface hydrology may be integral for modeling aspects of long‐term landscape evolution.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1016/j.earscirev.2022.103944
