Detection of senescence’s dynamics in crop breeding is time consuming and needs considerable details regarding its rate of progression and intensity. Normalized difference red-edge index (NDREI) along with four other spectral vegetative indices (SVIs) derived from unmanned aerial vehicle (UAV) based spatial imagery, were evaluated for rapid and accurate prediction of senescence. For this, 32 selected winter wheat genotypes were planted under full and limited irrigation treatments. Significant variations for all five SVIs: green normalize difference vegetation index (GNDVI), simple ratio (SR), green chlorophyll index (GCI), red-edge chlorophyll index (RECI), and normalized difference red-edge index (NDREI) among genotypes and between treatments, were observed from heading to late grain filling stages. The SVIs showed strong relationship (R² = 0.69 to 0.78) with handheld measurements of chlorophyll and leaf area index (LAI), while negatively correlated (R² = 0.75 to 0.77) with canopy temperature (CT) across the treatments. NDREI as a new SVI showed higher correlations with ground data under both treatments, similarly as exhibited by other four SVIs. There were medium to strong correlations (r = 0.23–0.63) among SVIs, thousand grain weight (TGW) and grain yield (GY) under both treatments. Senescence rate was calculated by decreasing values of SVIs from their peak values at heading stage, while variance for senescence rate among genotypes and between treatments could be explained by SVIs variations. Under limited irrigation, 10% to 15% higher senescence rate was detected as compared with full irrigation. Principle component analysis corroborated the negative association of high senescence rate with TGW and GY. Some genotypes, such as Beijing 0045, Nongda 5181, and Zhongmai 175, were selected with low senescence rate, stable TGW and GY in both full and limited irrigation treatments, nearly in accordance with the actual performance of these cultivars in field. Thus, SVIs derived from UAV appeared as a promising tool for rapid and precise estimation of senescence rate at maturation stages.

Plant height is an important selection target since it is associated with yield potential, stability and particularly with lodging resistance in various environments. Rapid and cost-effective estimation of plant height from airborne devices using a digital surface model can be integrated with academic research and practical wheat breeding programs. A bi-parental wheat population consisting of 198 doubled haploid lines was used for time-series assessments of progress in reaching final plant height and its accuracy was assessed by quantitative genomic analysis. UAV-based data were collected at the booting and mid-grain fill stages from two experimental sites and compared with conventional measurements to identify quantitative trait loci (QTL) underlying plant height. A significantly high correlation of R2 = 0.96 with a 5.75 cm root mean square error was obtained between UAV-based plant height estimates and ground truth observations at mid-grain fill across both sites. Correlations for UAV and ground-based plant height data were also very high (R2 = 0.84–0.85, and 0.80–0.83) between plant height at the booting and mid-grain fill stages, respectively. Broad sense heritabilities were 0.92 at booting and 0.90–0.91 at mid-grain fill across sites for both data sets. Two major QTL corresponding to Rht-B1 on chromosome 4B and Rht-D1 on chromosome 4D explained 61.3% and 64.5% of the total phenotypic variations for UAV and ground truth data, respectively. Two new and stable QTL on chromosome 6D seemingly associated with accelerated plant growth was identified at the booting stage using UAV-based data. Genomic prediction accuracy for UAV and ground-based data sets was significantly high, ranging from r = 0.47–0.55 using genome-wide and QTL markers for plant height. However, prediction accuracy declined to r = 0.20–0.31 after excluding markers linked to plant height QTL. This study provides a fast way to obtain time-series estimates of plant height in understanding growth dynamics in bread wheat. UAV-enabled phenotyping is an effective, high-throughput and cost-effective approach to understand the genetic basis of plant height in genetic studies and practical breeding.

Unmanned aerial vehicle (UAV) based remote sensing is a promising approach for non-destructive and high-throughput assessment of crop water and nitrogen (N) efficiencies. In this study, UAV was used to evaluate two field trials using four water (T0 = 0 mm, T1 = 80 mm, T2 = 120 mm, and T3 = 160 mm), and four N (T0 = 0, T1 = 120 kg ha^–1, T2 = 180 kg ha^–1, and T3 = 240 kg ha^–1) treatments, respectively, conducted on three wheat genotypes at two locations. Ground-based destructive data of water and N indictors such as biomass and N contents were also measured to validate the aerial surveillance results. Multispectral traits including red normalized difference vegetation index (RNDVI), green normalized difference vegetation index (GNDVI), normalized difference red-edge index (NDRE), red-edge chlorophyll index (RECI) and normalized green red difference index (NGRDI) were recorded using UAV as reliable replacement of destructive measurements by showing high r values up to 0.90. NGRDI was identified as the most efficient non-destructive indicator through strong prediction values ranged from R² = 0.69 to 0.89 for water use efficiencies (WUE) calculated from biomass (WUE.BM), and R² = 0.80 to 0.86 from grain yield (WUE.GY). RNDVI was better in predicting the phenotypic variations for N use efficiency calculated from nitrogen contents of plant samples (NUE.NC) with high R² values ranging from 0.72 to 0.94, while NDRE was consistent in predicting both NUE.NC and NUE.GY by 0.73 to 0.84 with low root mean square errors. UAV-based remote sensing demonstrates that treatment T2 in both water 120 mm and N 180 kg ha^–1 supply trials was most appropriate dosages for optimum uptake of water and N with high GY. Among three cultivars, Zhongmai 895 was highly efficient in WUE and NUE across the water and N treatments. Conclusively, UAV can be used to predict time-series WUE and NUE across the season for selection of elite genotypes, and to monitor crop efficiency under varying N and water dosages.

Grain yield is increasingly affected by climate factors such as drought and heat. To develop resilient and high-yielding cultivars, high-throughput phenotyping (HTP) techniques are essential for precise decisions in wheat breeding. The ability of unmanned aerial vehicle (UAV)-based multispectral imaging and ensemble learning methods to increase the accuracy of grain yield prediction in practical breeding work is evaluated in this study. For this, 211 winter wheat genotypes were planted under full and limited irrigation treatments, and multispectral data were collected at heading, flowering, early grain filling (EGF), and mid-grain filling (MGF) stages. Twenty multispectral vegetation indices (VIs) were estimated, and VIs with heritability greater than 0.5 were selected to evaluate the models across the growth stages under both irrigation treatments. A framework for ensemble learning was developed by combining multiple base models such as random forest (RF), support vector machine (SVM), Gaussian process (GP), and ridge regression (RR). The R² values between VIs and grain yield for individual base models were ranged from 0.468 to 0.580 and 0.537 to 0.598 for grain yield prediction in full and limited irrigation treatments across growth stages, respectively. The prediction results of ensemble models were ranged from 0.491 to 0.616 and 0.560 to 0.616 under full and limited irrigation treatments respectively, and were higher than that of the corresponding base learners. Moreover, the grain yield prediction results were observed high at mid grain filling stage under both full (R² = 0.625) and limited (R² = 0.628) irrigation treatments through ensemble learning based stacking of four base learners. Further improvements in ensemble learning models can accelerate the use of UAV-based multispectral data for accurate predictions of complex traits like grain yield in wheat.

Accurate forecasting of crop yields holds paramount importance in guiding decision-making processes related to breeding efforts. Despite significant advancements in crop yield forecasting, existing methods often struggle with integrating diverse sensor data and achieving high prediction accuracy under varying environmental conditions. This study focused on the application of multi-sensor data fusion and machine learning algorithms based on unmanned aerial vehicles (UAVs) in wheat yield prediction. Five machine learning (ML) algorithms, namely random forest (RF), partial least squares (PLS), ridge regression (RR), k-nearest neighbor (KNN) and extreme gradient boosting decision tree (XGboost), were utilized for multi-sensor data fusion, together with three ensemble methods including the second-level ensemble methods (stacking and feature-weighted) and the third-level ensemble method (simple average), for wheat yield prediction. The 270 wheat hybrids were used as planting materials under full and limited irrigation treatments. A cost-effective multi-sensor UAV platform, equipped with red–green–blue (RGB), multispectral (MS), and thermal infrared (TIR) sensors, was utilized to gather remote sensing data. The results revealed that the XGboost algorithm exhibited outstanding performance in multi-sensor data fusion, with the RGB + MS + Texture + TIR combination demonstrating the highest fusion performance (R² = 0.660, RMSE = 0.754). Compared with the single ML model, the employment of three ensemble methods significantly enhanced the accuracy of wheat yield prediction. Notably, the third-layer simple average ensemble method demonstrated superior performance (R² = 0.733, RMSE = 0.668 t ha⁻¹). It significantly outperformed both the second-layer ensemble methods of stacking (R² = 0.668, RMSE = 0.673 t ha⁻¹) and feature-weighted (R² = 0.667, RMSE = 0.674 t ha⁻¹), thereby exhibiting superior predictive capabilities. This finding highlighted the third-layer ensemble method’s ability to enhance predictive capabilities and refined the accuracy of wheat yield prediction through simple average ensemble learning, offering a novel perspective for crop yield prediction and breeding selection.