{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T18:51:40Z","timestamp":1781376700672,"version":"3.54.1"},"reference-count":44,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2020,8,21]],"date-time":"2020-08-21T00:00:00Z","timestamp":1597968000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["MAKE"],"abstract":"<jats:p>In this work, we developed a data-driven framework to predict near-surface (0\u20135 cm) soil moisture (SM) by mapping inputs from the Soil &amp; Water Assessment Tool to SM time series from NASA\u2019s Soil Moisture Active Passive (SMAP) satellite for the period 1 January 2016\u201331 December 2018. We developed a hybrid artificial neural network (ANN) combining long short-term memory and multilayer perceptron networks that were used to simultaneously incorporate dynamic weather and static spatial data into the training algorithm, respectively. We evaluated the generalizability of the hybrid ANN using training datasets comprising several watersheds with different environmental conditions, examined the effects of standard and physics-guided loss functions, and experimented with feature augmentation. Our model could estimate SM on par with the accuracy of SMAP. We demonstrated that the most critical learning of the physical processes governing SM variability was learned from meteorological time series, and that additional physical context supported model performance when test data were not fully encapsulated by the variability of the training data. Additionally, we found that when forecasting SM based on trends learned during the earlier training period, the models appreciated seasonal trends.<\/jats:p>","DOI":"10.3390\/make2030016","type":"journal-article","created":{"date-parts":[[2020,8,23]],"date-time":"2020-08-23T21:28:06Z","timestamp":1598218086000},"page":"283-306","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["A Hybrid Artificial Neural Network to Estimate Soil Moisture Using SWAT+ and SMAP Data"],"prefix":"10.3390","volume":"2","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3271-1782","authenticated-orcid":false,"given":"Katherine H.","family":"Breen","sequence":"first","affiliation":[{"name":"Department of Geosciences, Baylor University, Waco, TX 76798, USA"},{"name":"Goddard Space Flight Center, NASA, Greenbelt, MD 20771, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7955-0491","authenticated-orcid":false,"given":"Scott C.","family":"James","sequence":"additional","affiliation":[{"name":"Department of Geosciences, Baylor University, Waco, TX 76798, USA"},{"name":"Department of Mechanical Engineering, Baylor University, Waco, TX 76798, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joseph D.","family":"White","sequence":"additional","affiliation":[{"name":"Department of Biology, Baylor University, Waco, TX 76798, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peter M.","family":"Allen","sequence":"additional","affiliation":[{"name":"Department of Geosciences, Baylor University, Waco, TX 76798, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jeffery G.","family":"Arnold","sequence":"additional","affiliation":[{"name":"USDA-Agricultural Research Service, Temple, TX 76502, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2020,8,21]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"42200","DOI":"10.1109\/ACCESS.2020.2976199","article-title":"Explainable machine learning for scientific insights and discoveries","volume":"8","author":"Roscher","year":"2020","journal-title":"IEEE Access"},{"key":"ref_2","unstructured":"Karpatne, A., Watkins, W., Read, J., and Kumar, V. (2017). Physics-guided neural networks (PGNN): An application in lake temperature modeling. arXiv."},{"key":"ref_3","first-page":"19","article-title":"Informed machine learning\u2014Towards a taxonomy of explicit integration of knowledge into machine learning","volume":"18","author":"Mayer","year":"2019","journal-title":"Learning"},{"key":"ref_4","unstructured":"Raissi, M., Perdikaris, P., and Karniadakis, G.E. (2017). Physics informed deep learning (Part II): Data-driven discovery of nonlinear partial differential equations. arXiv."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Mosavi, A., Ozturk, P., and Chau, K.W. (2018). Flood prediction using machine learning models: Literature review. Water, 10.","DOI":"10.20944\/preprints201810.0098.v2"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1531","DOI":"10.1098\/rsta.2002.1016","article-title":"Floods in a changing climate: A review","volume":"360","author":"Hunt","year":"2002","journal-title":"Philos. Trans. R. Soc. Lond. Ser. A Math. Phys. Eng. Sci."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1665","DOI":"10.1016\/j.pnsc.2009.08.001","article-title":"Climate change impacts on crop yield, crop water productivity and food security\u2014A review","volume":"19","author":"Kang","year":"2009","journal-title":"Prog. Nat. Sci."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"812","DOI":"10.1126\/science.1185383","article-title":"Food security: The challenge of feeding 9 billion people","volume":"327","author":"Godfray","year":"2010","journal-title":"Science"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"789","DOI":"10.1146\/annurev-arplant-042817-040256","article-title":"Trends in global agricultural land use: Implications for environmental health and food security","volume":"69","author":"Ramankutty","year":"2018","journal-title":"Annu. Rev. Plant Biol."},{"key":"ref_10","unstructured":"Neitsch, S., Arnold, J., Kiniry, J., and Williams, J. (2011). Soil & Water Assessment Tool Theoretical Documentation. Version 2009, Texas Water Resource Institute. TWRI Report; Technical Report, TR-406."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1016\/0022-1694(84)90159-8","article-title":"Testing a physically-based flood forecasting model (TOPMODEL) for three UK catchments","volume":"69","author":"Beven","year":"1984","journal-title":"J. Hydrol."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"4322","DOI":"10.1175\/2009JCLI2832.1","article-title":"On the nature of soil moisture in land surface models","volume":"22","author":"Koster","year":"2009","journal-title":"J. Clim."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1016\/0022-1694(89)90101-7","article-title":"Changing ideas in hydrology\u2014The case of physically-based models","volume":"105","author":"Beven","year":"1989","journal-title":"J. Hydrol."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"eaau0323","DOI":"10.1126\/science.aau0323","article-title":"Machine learning for data-driven discovery in solid Earth geoscience","volume":"363","author":"Bergen","year":"2019","journal-title":"Science"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Nilawar, A.P., Calderella, C.P., Lakhankar, T.Y., Waikar, M.L., and Munoz, J. (2017). Satellite soil moisture validation using hydrological SWAT model: A case study of Puerto Rico, USA. Hydrology, 4.","DOI":"10.3390\/hydrology4040045"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"392","DOI":"10.1016\/j.jhydrol.2016.05.052","article-title":"Soil moisture deficit estimation using satellite multi-angle brightness temperature","volume":"539","author":"Zhuo","year":"2016","journal-title":"J. Hydrol."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"61","DOI":"10.4031\/002533204787522424","article-title":"Development of a real-time regional ocean forecast system with application to a domain off the U.S. East Coast","volume":"38","author":"Breaker","year":"2004","journal-title":"Mar. Technol. Soc. J."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Fereidoon, M., Koch, M., and Brocca, L. (2019). Predicting rainfall and runoff through satellite soil moisture data and SWAT modelling for a poorly gauged basin in Iran. Water, 11.","DOI":"10.3390\/w11030594"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"eaaw1147","DOI":"10.1126\/science.aaw1147","article-title":"Boltzmann generators: Sampling equilibrium states of many-body systems with deep learning","volume":"365","author":"Olsson","year":"2019","journal-title":"Science"},{"key":"ref_20","unstructured":"Riley, P. (2019, November 20). Three Pitfalls to Avoid in Machine Learning. Available online: https:\/\/www.nature.com\/articles\/d41586-019-02307-y."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"767","DOI":"10.1080\/2150704X.2020.1766724","article-title":"Are extreme soil moisture deficits captured by remotely sensed data retrievals?","volume":"11","author":"Breen","year":"2020","journal-title":"Int. J. Remote Sens. Lett."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1016\/j.rse.2017.01.021","article-title":"Validation of SMAP surface soil moisture products with core validation sites","volume":"191","author":"Colliander","year":"2017","journal-title":"Remote Sens. Environ."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"671","DOI":"10.1016\/j.jhydrol.2016.10.040","article-title":"Simultaneous assimilation of in situ soil moisture and streamflow in the SWAT model using the Extended Kalman Filter","volume":"543","author":"Sun","year":"2016","journal-title":"J. Hydrol."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"593","DOI":"10.1111\/1752-1688.12516","article-title":"Constraining SWAT calibration with remotely sensed evapotranspiration data","volume":"53","author":"Tobin","year":"2017","journal-title":"JAWRA J. Am. Water Resour. Assoc."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Rhanoui, M., Mikram, M., Yousfi, S., and Barzali, S. (2019). A CNN-BiLSTM model for document-level sentiment analysis. Mach. Learn. Knowl. Extr., 1.","DOI":"10.3390\/make1030048"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Zhang, X., Zhang, Q., Zhang, G., Nie, Z., Gui, Z., and Que, H. (2018). A novel hybrid data-driven model for daily land surface temperature forecasting using long short-term memory neural network based on ensemble empirical mode decomposition. Int. J. Environ. Res. Public Health, 15.","DOI":"10.3390\/ijerph15051032"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Rahman, S., Rasheed, A., and San, O. (2018). A hybrid analytics paradigm combining physics-based modeling and data-driven modeling to accelerate incompressible flow solvers. Fluids, 3.","DOI":"10.3390\/fluids3030050"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Bilgera, C., Yamamoto, A., Sawano, M., Matsukura, H., and Ishida, H. (2018). Application of convolutional long short-term memory neural networks to signals collected from a sensor network for autonomous gas source localization in outdoor environments. Sensors, 18.","DOI":"10.3390\/s18124484"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Leontjeva, A., and Kuzovkin, I. (2016, January 17\u201319). Combining static and dynamic features for multivariate sequence classification. Proceedings of the 2016 IEEE International Conference on Data Science and Advanced Analytics (DSAA), Montreal, QC, Canada.","DOI":"10.1109\/DSAA.2016.10"},{"key":"ref_30","unstructured":"Entekhabi, D., Yueh, S., O\u2019Neill, P., Kellogg, K., Alen, A., Bindlish, R., Brown, M., Chan, S., Colliander, A., and Crow, W.T. (2014). SMAP Handbook, JPL Publication."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.coastaleng.2018.03.004","article-title":"A machine learning framework to forecast wave conditions","volume":"137","author":"James","year":"2018","journal-title":"Coast. Eng."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"2662","DOI":"10.1002\/2017GL072716","article-title":"Enabling large-scale viscoelastic calculations via neural network acceleration","volume":"44","author":"DeVries","year":"2017","journal-title":"Geophys. Res. Lett."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Ahmmed, B., Mudunuru, M., Karra, S., James, S., and Vesselinov, V. (2020). A comparative study of machine learning models for predicting the state of reactive mixing. arXiv.","DOI":"10.1016\/j.jcp.2021.110147"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Nakano, K., and Chakraborty, B. (2019). Effect of data representation for time series classification\u2014A comparative study and a new proposal. Mach. Learn. Knowl. Extr., 1.","DOI":"10.3390\/make1040062"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"2222","DOI":"10.1109\/TNNLS.2016.2582924","article-title":"LSTM: A search space odyssey","volume":"28","author":"Greff","year":"2017","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Gers, F.A., Schmidhuber, J., and Cummins, F. (1999, January 7\u201310). Learning to forget: Continual prediction with LSTM. Proceedings of the 1999 Ninth International Conference on Artificial Neural Networks ICANN 99. (Conf. Publ. No. 470), Edinburgh, UK.","DOI":"10.1049\/cp:19991218"},{"key":"ref_38","unstructured":"Jozefowicz, R., Zaremba, W., and Sutskever, I. (2015, January 6\u201311). An empirical exploration of recurrent network architectures. Proceedings of the International Conference on Machine Learning, Lille, France."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1111\/1752-1688.12482","article-title":"Introduction to SWAT+, a completely restructured version of the soil and water assessment tool","volume":"53","author":"Bieger","year":"2017","journal-title":"JAWRA J. Am. Water Resour. Assoc."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"558","DOI":"10.1175\/1525-7541(2001)002<0558:SMMICM>2.0.CO;2","article-title":"Soil moisture memory in climate models","volume":"2","author":"Koster","year":"2001","journal-title":"J. Hydrometeorol."},{"key":"ref_41","first-page":"49","article-title":"Feature-based classification of time-series data","volume":"10","author":"Nanopoulos","year":"2001","journal-title":"Int. J. Comput. Res."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1145\/2379776.2379788","article-title":"Time-series data mining","volume":"45","author":"Esling","year":"2012","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Aigner, S., and K\u00f6rner, M. (2020). The importance of loss functions for increasing the generalization abilities of a deep learning-based next frame prediction model for traffic scenes. Mach. Learn. Knowl. Extr., 2.","DOI":"10.3390\/make2020006"},{"key":"ref_44","unstructured":"Hoffer, E., Hubara, I., and Soudry, D. (2017). Train longer, generalize better: Closing the generalization gap in large batch training of neural networks. arXiv."}],"container-title":["Machine Learning and Knowledge Extraction"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2504-4990\/2\/3\/16\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T10:05:00Z","timestamp":1760177100000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2504-4990\/2\/3\/16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,8,21]]},"references-count":44,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2020,9]]}},"alternative-id":["make2030016"],"URL":"https:\/\/doi.org\/10.3390\/make2030016","relation":{},"ISSN":["2504-4990"],"issn-type":[{"value":"2504-4990","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,8,21]]}}}