{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T16:39:26Z","timestamp":1778344766460,"version":"3.51.4"},"reference-count":37,"publisher":"MDPI AG","issue":"14","license":[{"start":{"date-parts":[[2024,7,21]],"date-time":"2024-07-21T00:00:00Z","timestamp":1721520000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Research on Intelligent Monitoring and Early Warning Technology for rice pests and diseases of the Sichuan Provincial Department of Science and Technology","award":["2022NSFSC0172"],"award-info":[{"award-number":["2022NSFSC0172"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Visible near-infrared spectroscopy (VNIR) is extensively researched for obtaining soil property information due to its rapid, cost-effective, and environmentally friendly advantages. Despite its widespread application and significant achievements in soil property analysis, current soil prediction models continue to suffer from low accuracy. To address this issue, we propose a convolutional neural network model that can achieve high-precision soil property prediction by creating 2D multi-channel inputs and applying a multi-scale spatial attention mechanism. Initially, we explored two-dimensional multi-channel inputs for seven soil properties in the public LUCAS spectral dataset using the Gramian Angular Field (GAF) method and various preprocessing techniques. Subsequently, we developed a convolutional neural network model with a multi-scale spatial attention mechanism to improve the network\u2019s extraction of relevant spatial contextual information. Our proposed model showed superior performance in a statistical comparison with current state-of-the-art techniques. The RMSE (R\u00b2) values for various soil properties were as follows: organic carbon content (OC) of 19.083 (0.955), calcium carbonate content (CaCO3) of 24.901 (0.961), nitrogen content (N) of 0.969 (0.933), cation exchange capacity (CEC) of 6.52 (0.803), pH in H2O of 0.366 (0.927), clay content of 4.845 (0.86), and sand content of 12.069 (0.789). Our proposed model can effectively extract features from visible near-infrared spectroscopy data, contributing to the precise detection of soil properties.<\/jats:p>","DOI":"10.3390\/s24144728","type":"journal-article","created":{"date-parts":[[2024,7,22]],"date-time":"2024-07-22T14:45:53Z","timestamp":1721659553000},"page":"4728","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Multi-Scale Spatial Attention-Based Multi-Channel 2D Convolutional Network for Soil Property Prediction"],"prefix":"10.3390","volume":"24","author":[{"given":"Guolun","family":"Feng","sequence":"first","affiliation":[{"name":"College of Information Engineering, Sichuan Agricultural University, Ya\u2019an 625014, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2402-7657","authenticated-orcid":false,"given":"Zhiyong","family":"Li","sequence":"additional","affiliation":[{"name":"College of Information Engineering, Sichuan Agricultural University, Ya\u2019an 625014, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2737-0821","authenticated-orcid":false,"given":"Junbo","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Information Engineering, Sichuan Agricultural University, Ya\u2019an 625014, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mantao","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Information Engineering, Sichuan Agricultural University, Ya\u2019an 625014, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2024,7,21]]},"reference":[{"key":"ref_1","first-page":"1","article-title":"Chemical fertilizers and their impact on soil health","volume":"Volume 2","author":"Pahalvi","year":"2021","journal-title":"Microbiota and Biofertilizers, Ecofriendly Tools for Reclamation of Degraded Soil Environs"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1080\/05704928.2013.811081","article-title":"The performance of visible, near-, and mid-infrared reflectance spectroscopy for prediction of soil physical, chemical, and biological properties","volume":"49","author":"Janik","year":"2014","journal-title":"Appl. Spectrosc. Rev."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"510","DOI":"10.1016\/j.still.2015.07.021","article-title":"Estimating the soil clay content and organic matter by means of different calibration methods of vis-NIR diffuse reflectance spectroscopy","volume":"155","author":"Nawar","year":"2016","journal-title":"Soil Tillage Res."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Yang, M., Xu, D., Chen, S., Li, H., and Shi, Z. (2019). Evaluation of machine learning approaches to predict soil organic matter and pH using Vis-NIR spectra. Sensors, 19.","DOI":"10.3390\/s19020263"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"271","DOI":"10.1007\/s12145-023-01168-4","article-title":"Using deep neural networks for evaluation of soil quality based on VIS\u2013NIR spectroscopy","volume":"17","author":"Safaie","year":"2024","journal-title":"Earth Sci. Inform."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2016, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., and Darrell, T. (2015, January 7\u201312). Fully convolutional networks for semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2015, Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Tang, D., Wei, F., Qin, B., Liu, T., and Zhou, M. (2014, January 23\u201324). Coooolll: A deep learning system for twitter sentiment classification. Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014), Dublin, Ireland.","DOI":"10.3115\/v1\/S14-2033"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1016\/j.csl.2016.06.007","article-title":"Building DNN acoustic models for large vocabulary speech recognition","volume":"41","author":"Maas","year":"2017","journal-title":"Comput. Speech Lang."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Carvalho, M., Cardoso-Fernandes, J., Lima, A., and Teodoro, A.C. (2024). Convolutional Neural Networks Applied to Antimony Quantification via Soil Laboratory Reflectance Spectroscopy in Northern Portugal: Opportunities and Challenges. Remote Sens., 16.","DOI":"10.20944\/preprints202402.1438.v1"},{"key":"ref_11","first-page":"e220012","article-title":"Investigating the fidelity of explainable artificial intelligence methods for applications of convolutional neural networks in geoscience","volume":"1","author":"Mamalakis","year":"2022","journal-title":"Artif. Intell. Earth Syst."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Veres, M., Lacey, G., and Taylor, G.W. (2015, January 3\u20135). Deep learning architectures for soil property prediction. Proceedings of the 2015 12th Conference on Computer and Robot Vision, Halifax, NS, Canada.","DOI":"10.1109\/CRV.2015.15"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"115366","DOI":"10.1016\/j.geoderma.2021.115366","article-title":"Soil properties: Their prediction and feature extraction from the LUCAS spectral library using deep convolutional neural networks","volume":"402","author":"Zhong","year":"2021","journal-title":"Geoderma"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"3639","DOI":"10.1109\/TGRS.2016.2636241","article-title":"Deep recurrent neural networks for hyperspectral image classification","volume":"55","author":"Mou","year":"2017","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"176","DOI":"10.1002\/jrs.5750","article-title":"Transfer-learning-based Raman spectra identification","volume":"51","author":"Zhang","year":"2020","journal-title":"J. Raman Spectrosc."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"e00233","DOI":"10.1016\/j.geodrs.2019.e00233","article-title":"Estimation of soil properties from the EU spectral library using long short-term memory networks","volume":"18","author":"Singh","year":"2019","journal-title":"Geoderma Reg."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"114616","DOI":"10.1016\/j.geoderma.2020.114616","article-title":"Combination of convolutional neural networks and recurrent neural networks for predicting soil properties using Vis\u2013NIR spectroscopy","volume":"380","author":"Yang","year":"2020","journal-title":"Geoderma"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"e00198","DOI":"10.1016\/j.geodrs.2018.e00198","article-title":"Using deep learning to predict soil properties from regional spectral data","volume":"16","author":"Padarian","year":"2019","journal-title":"Geoderma Reg."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Li, R., Yin, B., Cong, Y., and Du, Z. (2020). Simultaneous prediction of soil properties using multi_cnn model. Sensors, 20.","DOI":"10.3390\/s20216271"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"116555","DOI":"10.1016\/j.geoderma.2023.116555","article-title":"An innovative approach for integrating two-dimensional conversion of Vis-NIR spectra with the Swin Transformer model to leverage deep learning for predicting soil properties","volume":"436","author":"Jin","year":"2023","journal-title":"Geoderma"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"331","DOI":"10.1007\/s41095-022-0271-y","article-title":"Attention mechanisms in computer vision: A survey","volume":"8","author":"Guo","year":"2022","journal-title":"Comput. Vis. Media"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"102417","DOI":"10.1016\/j.inffus.2024.102417","article-title":"Visual attention methods in deep learning: An in-depth survey","volume":"108","author":"Hassanin","year":"2024","journal-title":"Inf. Fusion"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., and He, K. (2018, January 18\u201323). Non-local neural networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2018, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"114967","DOI":"10.1016\/j.geoderma.2021.114967","article-title":"Using autoencoders to compress soil VNIR\u2013SWIR spectra for more robust prediction of soil properties","volume":"393","author":"Tsimpouris","year":"2021","journal-title":"Geoderma"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"7000805","DOI":"10.1109\/LGRS.2022.3201266","article-title":"Attention-Based CNN Ensemble for Soil Organic Carbon Content Estimation with Spectral Data","volume":"19","author":"Zhao","year":"2022","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"114208","DOI":"10.1016\/j.geoderma.2020.114208","article-title":"Simultaneous prediction of soil properties from VNIR-SWIR spectra using a localized multi-channel 1-D convolutional neural network","volume":"367","author":"Tsakiridis","year":"2020","journal-title":"Geoderma"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"140","DOI":"10.1111\/ejss.12499","article-title":"LUCAS Soil, the largest expandable soil dataset for Europe: A review","volume":"69","author":"Orgiazzi","year":"2018","journal-title":"Eur. J. Soil Sci."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"329","DOI":"10.1016\/j.landusepol.2011.07.003","article-title":"European Soil Data Centre: Response to European policy support and public data requirements","volume":"29","author":"Panagos","year":"2012","journal-title":"Land Use Policy"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"7409","DOI":"10.1007\/s10661-013-3109-3","article-title":"The LUCAS topsoil database and derived information on the regional variability of cropland topsoil properties in the European Union","volume":"185","author":"Jones","year":"2013","journal-title":"Environ. Monit. Assess."},{"key":"ref_30","unstructured":"Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv."},{"key":"ref_31","unstructured":"Wang, Z., and Oates, T. (2015). Imaging time-series to improve classification and imputation. arXiv."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Guo, C., Li, H., and Pan, D. (2010). An improved piecewise aggregate approximation based on statistical features for time series mining. Knowledge Science, Engineering and Management Proceedings of the 4th International Conference, KSEM 2010, Belfast, Northern Ireland, UK, 1\u20133 September 2010, Springer. Proceedings 4.","DOI":"10.1007\/978-3-642-15280-1_23"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Liu, Z., Mao, H., Wu, C.Y., Feichtenhofer, C., Darrell, T., and Xie, S. (2022, January 18\u201324). A convnet for the 2020s. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition 2022, New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"415","DOI":"10.1007\/s41095-022-0274-8","article-title":"Pvt v2: Improved baselines with pyramid vision transformer","volume":"8","author":"Wang","year":"2022","journal-title":"Comput. Vis. Media"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Yu, W., Luo, M., Zhou, P., Si, C., Zhou, Y., Wang, X., Feng, J., and Yan, S. (2022, January 18\u201324). Metaformer is actually what you need for vision. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition 2022, New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.01055"},{"key":"ref_36","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., and Gelly, S. (2020). An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale. arXiv."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"105684","DOI":"10.1016\/j.still.2023.105684","article-title":"Predicting key soil properties from Vis-NIR spectra by applying dual-wavelength indices transformations and stacking machine learning approaches","volume":"229","author":"Tavakoli","year":"2023","journal-title":"Soil Tillage Res."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/14\/4728\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T15:20:39Z","timestamp":1760109639000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/14\/4728"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,21]]},"references-count":37,"journal-issue":{"issue":"14","published-online":{"date-parts":[[2024,7]]}},"alternative-id":["s24144728"],"URL":"https:\/\/doi.org\/10.3390\/s24144728","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7,21]]}}}