Machine learning applications for landscape management and conservation: Using digital elevation data to model locations of natural and cultural features

Abstract:

This project entails creating a series of supervised machine learning models to predict the locations of caves and two different types of archaeological features using digital elevation data. The goal of this work is to bridge the gap between the field of machine learning pursued by computer scientists and the types of on-the-ground projects of interest to earth scientists and others who seek to improve management and conservation practices. This project began in 2018 with the goal of creating a targeted method of finding cave entrances in the dense tropical forest of Guatemala and Belize. In 2019, we used a random forest classifier, airborne laser scanning (ALS) data, and a training dataset of known caves to successfully identify several previously undocumented caves in northwestern Belize. Building on this work, modeling has been expanded to include other types of hidden and obscured features that colleagues are interested in studying. These include ancient Maya archaeological features in Guatemala and Mexico and shipwrecks off the coast of the United States. The models for the archaeological features are based on existing convolutional neural network architectures and make use of transfer learning. The Maya archaeological feature model uses ALS data as input. The shipwreck model, which is being completed under the aegis of the Navy’s Underwater Archaeology Branch (UA), is based on open source topo-bathymetric data and shipwreck data available from NOAA’s Data Access Viewer and NOAA’s Wrecks and Obstructions Database, as well as UA’s records. These models can be used to create more accurate maps of natural and archaeological features to aid management objectives, study patterns across the landscape, and find new features. Such models can easily be adjusted to identify other types of features, even using multispectral or RGB imagery as input. This work seeks to make machine learning methods accessible to non-computer scientists interested in study, management, and/or conservation of the landscape.