Estimating soil mineral nitrogen from data-sparse field experiments using crop model-guided deep learning approach

Rishabh Gupta, Satya K. Pothapragada, Weihuang Xu, Prateek Kumar Goel, Miguel A. Barrera, Mira S. Saldanha, Joel B. Harley, Kelly T. Morgan, Alina Zare, Lincoln Zotarelli

Abstract: Highlights•A hybrid modeling approach was proposed to estimate daily soil mineral nitrogen (SMN).•The hybrid-LSTM model was an integration of DSSAT and LSTM models.•Hybrid model was trained using DSSAT simulated and observed SMN.•Hybrid model outperformed DSSAT, offering reliable SMN estimates in potato fields.•Developed hybrid model could provide crop nutrient recommendations.