PhysCrop-Risk: Progress-Aligned Sequential Risk Control for Early Crop Monitoring

Early crop monitoring requires repeated decisions from irregular observations before harvest. Two challenges arise: calendar time poorly reflects crop development, and repeated decisions accumulate false alarms even when each is calibrated separately. We present PhysCrop-Risk, a progress aligned framework that uses growing degree days (GDD) to define causal observation boundaries and decision checkpoints, aligns Sentinel-2 and weather observations on a common thermal scale, and calibrates low yield evidence over the full season. At three crop specific checkpoints, risk scores are converted into empirical one sided $p$-values against held out normal yield fields, and a shared significance budget controls the probability of at least one false watch. Two consecutive crossings define a more conservative action tier. On 2,171 fields spanning four countries, four crops, and nine seasons, the final checkpoint on a 322 field audit reaches an AUROC of $0.8331$ and an AUPRC of $0.6245$ at a median lead time of $62.5$ days before harvest. Under the frozen protocol, watch and persistent-action tiers achieve field season false positive rates of $5.24\%$ and $2.02\%$, with the watch confidence interval covering the $5\%$ budget. An exploratory post hoc calibration analysis yields $4.84\%$ and $1.61\%$ but does not inherit the finite sample guarantee. These results show that progress aware alignment and sequence level calibration can turn partial season observations into reliable early crop risk decisions.