{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/soil-texture-classification-with-1d","title":"Soil Texture Classification with 1D Convolutional Neural Networks based on Hyperspectral Data","arxiv_id":"1901.04846","date":"2019-01-15","proceeding":null,"authors":["Felix M. Riese","Sina Keller"],"abstract":"Soil texture is important for many environmental processes. In this paper, we\nstudy the classification of soil texture based on hyperspectral data. We\ndevelop and implement three 1-dimensional (1D) convolutional neural networks\n(CNN): the LucasCNN, the LucasResNet which contains an identity block as\nresidual network, and the LucasCoordConv with an additional coordinates layer.\nFurthermore, we modify two existing 1D CNN approaches for the presented\nclassification task. The code of all five CNN approaches is available on GitHub\n(Riese, 2019). We evaluate the performance of the CNN approaches and compare\nthem to a random forest classifier. Thereby, we rely on the freely available\nLUCAS topsoil dataset. The CNN approach with the least depth turns out to be\nthe best performing classifier. The LucasCoordConv achieves the best\nperformance regarding the average accuracy. In future work, we can further\nenhance the introduced LucasCNN, LucasResNet and LucasCoordConv and include\nadditional variables of the rich LUCAS dataset.","url_abs":"http://arxiv.org/abs/1901.04846v3","url_pdf":"http://arxiv.org/pdf/1901.04846v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"soil-texture-classification-with-1d","repo_url":"https://github.com/felixriese/CNN-SoilTextureClassification","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"texture-classification","task_name":"Texture Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}