3908de88-273c-4053-85fc-aac8eb757df0 urn:uuid en UTF-8 nonGeographicDataset nonGeographicDataset 2025-10-16T10:58:57 creation ISO 19115 2016 Revised weathering intensity model of Australia 3908de88-273c-4053-85fc-aac8eb757df0 Weathering is an important process of the Earth’s surface that has a major influence on the chemical and physical properties of rock and soil. The intensity of this process largely controls the degree to which primary minerals are altered to secondary components, including clay and oxide minerals. The degree of surface weathering is particularly important in Australia, where variations in weathering intensity correspond to differences in the nature and distribution of regolith (weathered bedrock and sediments), which mantles approximately 80% of the Australian continent. Here, I use a random forest decision tree machine learning algorithm to first establish a relationship between field estimates of the degree of weathering and a comprehensive suite of covariate or predictive datasets. I then apply this relationship to generate an improved national model of surface to near-surface weathering intensity. Covariates include satellite imagery, terrain attributes, airborne radiometric imagery and mapped geology. The model performs very well, with an r-squared correlation of 0.85 based on 5 K-fold cross-validation on the mean and standard deviation of 300 random forest models. This new weathering intensity model has broad utility for mineral exploration in variably weathered landscapes, agricultural mapping of chemical and physical soil attributes, ecology, and advancing the understanding of weathering processes within the upper regolith. Citation: Wilford, J., 2020. Revised weathering intensity model of Australia. In: Czarnota, K., Roach, I., Abbott, S., Haynes, M., Kositcin, N., Ray, A. and Slatter, E. (eds.) Exploring for the Future: Extended Abstracts, Geoscience Australia, Canberra, 1–4. {"type": "Polygon", "coordinates": [[[111.5982, -45.3367], [154.8404, -45.3367], [154.8404, -8.7548], [111.5982, -8.7548], [111.5982, -45.3367]]]} 111.5982 154.8404 -45.3367 -8.7548 Data analytics EARTH SCIENCES EftF Exploring for the Future Machine Learning Published_External Regolith Surface Weathering geophysics Extended Abstract for download (pdf) [4.7 MB] documentDigital Extended Abstract for download (pdf) [4.7 MB] PDF