Lentils in Australia are primarily grown in temperate and Mediterranean climates, especially in the southern and western regions of the country. As in other parts of the world, lentil yields in these areas are significantly influenced by factors such as frost, heat, and drought, contributing to variable production. Therefore, selecting appropriate lentil varieties and determining optimal sowing times that align with favourable growing conditions is crucial. Accurate predictions of crop development are essential in this context. Current models mainly rely on photoperiod and temperature to predict lentil phenology; however, they often neglect the impact of soil water on flowering and pod set. This study investigated whether incorporating soil water as an additional factor could improve predictions for these critical growth stages. The modified model was tested using 281 data points from various lentil experiments that examined the timing of flowering (61-147 days) and pod set (77-163 days) across different combinations of location, variety, sowing time, and season. The results indicated that including soil water in the prediction model achieved an R2 value of 0.84 for flowering and 0.83 for pod set. The normalised root mean square error (NRMSE) was 0.07, and Lin's concordance correlation coefficient (LinCCC) was 0.91. The model produced an R2 of 0.88, an NRMSE of 0.05, and a LinCCC of 0.93 flowering compared to the default model, which yielded an R2 of 0.24, an NRMSE of 0.17, and a LinCCC of 0.36 for flowering. A limited sensitivity analysis of the modified model showed that variations in initial soil water and in-season rainfall significantly affected the timing of flowering and pod set. Additionally, we employed a probability framework to assess the crop's vulnerability to the last frost day and early heat stress events during the reproductive stage. This approach provided valuable insights for decision-making to mitigate risks associated with frost and heat stress. Our study suggests that integrating soil water dynamics into lentil phenology models improves the accuracy and precision of predictions regarding the timing of flowering and pod set. These improvements lead to better forecasts, ultimately helping to minimise damage from frost and heat stress during lentil cultivation and can better explain the effect of climate variability.

Bread wheat and durum wheat genotypes were grown in field experiments at two locations in New South Wales, Australia across several years and using two sowing times ('early' v. 'late'). Genotypes were grouped based on genetic similarity. Grain yield, grain size, soil characteristics and daily weather data were collected. The weather data were used to calculate water and heat stress indices for four key growth periods around flowering. Least absolute shrinkage and selection operator (LASSO) was used to predict grain yield and to identify the most influential features (a combination of index and growth period). A novel approach involving the crop water supply-demand ratio effectively summarized water relations during growth. LASSO predicted grain yield quite well (adjusted R-2 from 0.57 to 0.98), especially in a set of durum genotypes. However, the addition of other important variables such as lodging score, disease incidence, weed incidence and insect damage could have improved modelling results. Growth period 2 (30 days pre-flowering up to flowering) was the most sensitive for yield loss from heat stress and water stress for most features. Although one group of bread wheat genotypes was more sensitive to water stress (drought) in period 3 (20 days pre-flowering to 10 days post-flowering). Evapotranspiration was a significant positive feature but only in the vegetative phase (pre-flowering, period 1). This study confirms the usefulness of LASSO modelling as a technique to make predictions that could be used to identify genotypes that are suitable candidates for further investigation by breeders for their stress-tolerance ability.