I develop computational tools for analysis of field data. The output of my most mature projects make it onto this page. See also my github page.
“Deep” Optical Wave Gauging
Software and data for training deep convolutional neural network models to estimate wave height and wave period from the same imagery
detailed in the paper:
Buscombe, Carini, Harrison, Chickadel, and Warrick (in review) Optical wave gauging with deep neural networks. Submitted to Coastal Engineering
More details soon …
A tool for web-based image annotation and efficient labeling pixels in images
Implements a rapid technique, described by Buscombe & Ritchie, (2018), for dense image labeling based on limited manual annotations.
"DL-Tools" is a new open-source project dedicated to provide a Python framework for image recognition and semantic image classification using deep convolutional neural networks.
More details soon ...
Buscombe, D. and Ritchie, A. (2018) Landscape Classification with Deep Neural Networks. Geosciences 8(7), 244; https://doi.org/10.3390/geosciences8070244
PriSM (Probabilistic acoustic Sediment Mapping)
PriSM is an open-source project dedicated to provide a Python framework to supervised classification of sediment and substrate from multibeam acoustic backscatter data, implementing the following methods:
Buscombe, D. and Grams, P.E. (2018) Probabilistic substrate classification with conditional random fields of acoustic backscatter. Geosciences
Buscombe, D., Grams, P.E., Kaplinski, M. (2017) Compositional signatures in acoustic backscatter over vegetated and unvegetated mixed sand-gravel riverbeds. Journal of Geophysical Research - Earth Surface 122, 1771-1793.
Digital Grain Size Online
pyDGS is an open-source project dedicated to provide a Python framework to compute estimates of grain size distribution using the continuous wavelet transform method of Buscombe (2013) from an image of sediment where grains are clearly resolved. DOES NOT REQUIRE CALIBRATION
This program implements the algorithm of:
Buscombe, D. (2013) Transferable Wavelet Method for Grain-Size Distribution from Images of Sediment Surfaces and Thin Sections, and Other Natural Granular Patterns. Sedimentology 60, 1709-1732. Download here
A Python framework for reading and processing data from a Humminbird low-cost sidescan sonar
PyHum is an open-source project dedicated to provide a generic Python framework for reading and exporting data from Humminbird(R) instruments, carrying out rudimentary radiometric corrections to the data, classify bed texture, and produce some maps on aerial photos and kml files for google-earth.
The software is designed to read Humminbird data (.SON, .IDX, and .DAT files) and works on both sidescan and downward-looking echosounder data, where available.
If you use PyHum in your published work, please cite the following papers:
Buscombe, D., Grams, P.E., and Smith, S. (2015) "Automated riverbed sediment classification using low-cost sidescan sonar", Journal of Hydraulic Engineering, 10.1061/(ASCE)HY.1943-7900.0001079, 06015019. Download here
Buscombe, D., 2017, Shallow water benthic imaging and substrate characterization using recreational-grade sidescan-sonar. ENVIRONMENTAL MODELLING & SOFTWARE 89, 1-18. Download here
PySESA is an open-source project dedicated to provide a generic Python framework for spatially explicit statistical analyses of point clouds and other geospatial data, in the spatial and frequency domains, for use in the geosciences
The program is detailed in: Buscombe, D. “Spatially explicit spectral analysis of point clouds and geospatial data” Computers and Geosciences 86, 92-108. Download here
Program for Interactive Sandbar Segmentation using GrabCut algorithm. For interactive segmentation of sandbars in imagery from remote cameras in Grand Canyon. Accompanies the following report:
Grams, Tusso, Buscombe (2018) Automated Remote Cameras for Monitoring Alluvial Sandbars on the Colorado River in Grand Canyon, Arizona. U.S. Geological Survey Open File Report 2017