Hybrid MSRM-Based Deep Learning and Multitemporal Sentinel 2-Based Machine Learning Algorithm
JavaScript code to be implemented in Google Earth Engine(c) for Hybrid MSRM-Based Deep Learning and Multitemporal Sentinel 2-Based Machine Learning Algorithm.<br/> <br>Algorithm for large-scale automatic detection of burial mounds, one of the most common types of archaeological sites glo...
| Autor: | |
|---|---|
| Tipo de recurso: | conjunto de datos |
| Fecha de publicación: | 2022 |
| País: | España |
| Institución: | Consorci de Serveis Universitaris de Catalunya (CSUC) |
| Repositorio: | CORA.Repositori de Dades de Recerca |
| OAI Identifier: | oai:dnet:cora.rdr____::105be10f4d4df6464ead7c93d1b92b39 |
| Acceso en línea: | https://doi.org/10.34810/DATA242 |
| Access Level: | acceso abierto |
| Palabra clave: | Arts and Humanities Computer and Information Science tumuli mounds archaeology deep learning Google Earth Engine |
| Sumario: | JavaScript code to be implemented in Google Earth Engine(c) for Hybrid MSRM-Based Deep Learning and Multitemporal Sentinel 2-Based Machine Learning Algorithm.<br/> <br>Algorithm for large-scale automatic detection of burial mounds, one of the most common types of archaeological sites globally, using LiDAR and multispectral satellite data. Although previous attempts were able to detect a good proportion of the known mounds in a given area, they still presented high numbers of false positives and low precision values. Our proposed approach combines random forest for soil classification using multitemporal multispectral Sentinel-2 data and a deep learning model using YOLOv3 on LiDAR data previously pre-processed using a multi–scale relief model. The resulting algorithm significantly improves previous attempts with a detection rate of 89.5%, an average precision of 66.75%, a recall value of 0.64 and a precision of 0.97, which allowed, with a small set of training data, the detection of 10,527 burial mounds over an area of near 30,000 km2, the largest in which such an approach has ever been applied. The open code and platforms employed to develop the algorithm allow this method to be applied anywhere LiDAR data or high-resolution digital terrain models are available.<br/> |
|---|