Yield prediction in wheat cultivated under semi-arid climatic conditions is gaining increasing importance for sustainable production strategies and decision support systems. In this study, a time-series-based modeling approach was implemented using sensor-based data (SPAD, NSPAD, NDVI, INSEY, and plant height measurements collected at four different Zadoks growth stages (ZD24, ZD30, ZD31, and ZD32). Five different machine learning algorithms (Random Forest, Gradient Boosting, AdaBoost, LightGBM, and XGBoost) were tested individually for each stage, and the model performances were evaluated using statistical metrics such as R²%, RMSE t/ha, and MAE t/ha. Modeling results revealed that the ZD31 stage (first node detectable) was identified as the most successful phase for prediction accuracy, with the XGBoost model achieving the highest R²% score (81.0). In the same model, RMSE and MAE values were calculated as 0.49 and 0.37, respectively. The LightGBM model also showed remarkable performance during the ZD30 stage, achieving an R²% of 78.0, an RMSE of 0.52, and an MAE of 0.40. The SHAP (SHapley Additive exPlanations) method used to interpret feature importance revealed that the NDVI and INSEY indices contributed the most significant values to prediction accuracy for yield. This study demonstrates that phenology-sensitive yield prediction approaches offer high potential for sensor-based digital applications. Furthermore, the integration of timing, model selection, and explainability provided valuable insights for the development of advanced decision support systems.

Frike is an ancient and traditional food product prepared from early harvested whole wheat grain, particularly durum wheat (DW). Due to its many health beneficial effects, frike is considered a functional food. It is also a lucrative commodity, produced in various West Asian and North African countries and typically in Southeastern Turkey. However, no systematic assessment of the most-suitable genotypes for frike production in the region is available. This study aimed to carry out such an evaluation, based on frike yield, quality traits, marketing price, and profitability, on a set of 20 DW cultivars and DW-Thinopyrum ponticum introgression lines (ILs). The results based on a field trial performed in Gölbaşı (Adıyaman, Turkey) in the 2021–2022 season revealed the Turkish varieties Tüten-2002, Edessa, Artuklu, and Perre, together with the R5 IL to have the highest frike yields measured on 3 kg of roasted fresh spikes. The highest marketing prices were obtained by Turkish varieties Sariçanak-98, Burgos, Sümerli, and Artuklu, along with the R112 IL, excelling in quality traits. Considering all parameters, the Turkish cultivars Artuklu, Firat-93, and Sariçanak-98, besides the R112 IL, resulted in being the most-convenient genotypes for frike making, thus representing good candidates for maintaining cultural and genetic diversity in food production from a staple crop such as DW.

Triticale is a cereal that currently has a cultivated global area of approximately 3.8 Mha. It is widely used as a feed and forage crop. Although winter triticale cultivars are planted in Poland, Germany and Belarus (the main producers), a significant portion of their cultivation is carried out in the Mediterranean basin using spring cultivars. Spain and Türkiye are two examples of the success of this crop in terms of promotion, breeding, and expansion. Thus, in 2022/23, 280,000 hectares of triticale were planted in Spain, while 100,000 hectares were planted in Türkiye, ranking 5th and 8th in the world, respectively. Current triticale cultivars have high grain and/or forage yield. Furthermore, dual-purpose cultivars are available and can be intercropped with legumes, which increases their possibilities in the field. Triticale competes well with weeds and is resistant to many diseases. It performs well in acidic soils, and it is tolerant to drought, conditions common in the Mediterranean basin. In the future, funding for spring triticale breeding programs (which are scarce and declining) should be maintained, and projects to improve agronomic techniques and publicize the advantages of this crop could be implemented. Furthermore, the use of triticale for human food could expand in the region, especially in MENA countries.

Physiological, Morphological, Phenological and Yield Evaluation of Durum Wheat Lines Under Rainfed Conditions