Contribution of new and old phosphorus from organic and inorganic fertilizers in subsurface-drained fields using machine learning.

Phosphorus (P) is essential for crop growth but leaches through subsurface
drainage discharge, impacting water quality. This study’s objectives are:
(1) apply machine learning to quantify the contributions of incidental
(new) and legacy (old) P in drainage discharge from Organic site and
Inorganic site, and (2) evaluate the effect of manure application timing
on P loss. We collected data from two on-farm sites in southeast Michigan,
USA. We applied the Weighted Regression on Discharge and Seasons (WRDS)
equation to analyze P load based on drainage discharge and fertilizer
application timing. The data was divided into calibration and validation
sets, and machine learning was employed for training. The results showed
strong model prediction performance. Organic fertilizers contributed
approximately twice the total phosphorus (TP) loss (7.54 kg ha⁻¹ vs. 3.73
kg ha⁻¹) and nearly four times the dissolved reactive phosphorus (DRP)
loss (4.90 kg ha⁻¹ vs. 1.05 kg ha⁻¹) compared to inorganic P loss. When
applied during winter months (Dec-Jan), organic fertilizer contributed to
greater new P loss, whereas early fall applications (Oct-Nov) resulted in
lower new P loss, showing the importance of application timing. At the
Organic site, legacy P was the dominant contributor to total phosphorus
(TP) and dissolved reactive phosphorus (DRP) losses, accounting for 84%
and 79% of losses, respectively. At the Inorganic site, Legacy P was
responsible for 97% of TP loss and the entirety (100%) of DRP loss. In
conclusion, legacy P was the dominant source of P loss through drainage
discharge, and timing of organic fertilizer application significantly
influenced new P loss.