Satellite soil-moisture retrievals are increasingly used to trigger irrigation advisories, yet their reliability degrades when vegetation regrowth shifts the relationship between brightness temperature and surface moisture. The framework is formalised through a weighted conformal predictor whose weights are estimated from a density-ratio model, and a coverage theorem is proved under a bounded density-ratio assumption. A climate-analytics evaluation protocol is specified for irrigation-trigger reliability, distinguishing false-alarm exposure from missed-irrigation exposure. Using NASA POWER monthly reanalysis for Lagos, Nigeria (2000–2023, 312 monthly observations), the analysis reports a mean air temperature of 26.414 °C and a warming trend of 0.1553 °C per decade, which motivates the vegetation-regrowth regime as a realistic non-stationary setting. The contribution is a calibration procedure that restores conditional coverage under vegetation shift and a decision-theoretic account of when conformal intervals should and should not be used to trigger irrigation.
No takes yet. Share an insight, caveat, or question.
Amankwah et al. (2026) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: