The Forecasting Yield of Highland Barley and Wheat by Combining a Crop Model with Different Weather Fusion Methods in the Study of the Northeastern Tibetan Plateau

Obtaining precise seasonal yield estimates is challenging, with weather forecast accuracy being a key factor. This study examines the impact of different weather data forecasting methods on yield estimation. Initially, we evaluated the suitability of the WOFOST model for highland barley (HB) and wheat on the northeastern Tibetan Plateau. Yield forecasts were conducted using nine historical weather selection methods under two scenarios, differing in their use of 10-day TIGGE data. The results showed that different weather data fusion methods led to varying forecasted yields. For HB, sequential selection and an improved KNN algorithm were optimal, while for wheat, sequential selection performed best. Early-season forecasts had lower accuracy, while predictions after flowering were more reliable. Incorporating TIGGE short-term forecasts into historical weather data improved HB yield forecasts, with 98.2% of days having an average relative error (ARE) below 20%. For wheat, using only historical weather data provided more stable yield forecasts, with 93.1% of days having an ARE below 20%. The weather data fusion strategy for yield forecasts offered reliable prediction accuracy without the need for full-cycle weather observation.