The Potential of a Precision Agriculture (PA) Practice for In Situ Evaluation of Herbicide Efficacy and Selectivity in Durum Wheat (Triticum durum Desf.)

Abstract

Precision agriculture (PA) practices based on the use of sensors and vegetation indices have great potential for optimizing herbicide use and improving weed management in field crops. The objective of this research was to evaluate the efficacy of commercial herbicide products and their selectivity in durum wheat by measuring the Normalized Difference Vegetation Index (NDVI). Field trials were conducted in Velestino and Kozani, Greece (2020–2021 and 2021–2022) in four site-years with the following treatment list: untreated control (T1), 2,4-D at 300 and 600 g a.e. ha−1 (T2 and T3, respectively), pyroxsulam + florasulam at 18.82 + 3.71 g a.i. ha−1 + cloquintocet-mexyl at 18.82 g a.i. ha−1 (T4), and mesosulfuron-methyl + iodosulfuron-methyl-sodium at 15 + 3 g a.i. ha−1 + mefenpyr-diethyl at 45 g a.i. ha−1 (T5). Site-years and treatments affected weed NDVI, weed biomass, crop NDVI, and grain yield (p ≤ 0.05). At Kozani, weed NDVI was lowest in T4 plots in 2020–2021 (0.31) and 2021–2022 (0.33). Treatments T4 and T5 resulted in lowest weed biomass in 2020-2021 (14–16 g m−2) and 2020-2021 (19–22 g m−2). At Velestino, T3 reduced weed biomass by 92 and 87% when compared to T5 in 2020–2021 and 2021–2022, respectively. Approximately, 67% and 73% of the variability in weed biomass in 2020–2021 and 2021–2022, respectively, at Kozani could be explained by weed NDVI. These parameters were strongly correlated in Velestino (R2 ≥ 90%). Low crop NDVI at Kozani indicated herbicide injury in T3 plots, confirmed by yield losses. During 2020-2021, yield was 30, 38, and 40% higher in T4 plots than in T2, T1, and T3 plots, respectively. At Velestino, yield in T1 plots was 25, 27, 27, and 29% lower than in T2, T4, T5, and T3 plots, respectively, in 2020–2021. Similar results were obtained in 2021–2022. The current study indicates that NDVI can be used as a reliable, non-subjective indicator of herbicide efficacy and selectivity in winter cereals. The methodology used in this work should also be evaluated in other crops and under different soil and climatic conditions.

Quick In Situ Evaluation of Herbicide Efficacy in Maize (Zea mays L.) Crop

“…On the contrary, there were no significant differences between the experimental years (ns; p > 0.05). All herbicide treatments reduced the weed NDVI values across the growing seasons, exactly as found in previous studies [20][21][22]. For the first experimental year, the lowest value (0.48) was recorded in plots treated with nicosulfuron + rimsulfuron + dicamba (T3) at 14 DAT.…”

“…However, this is the first time that the early-measured NDVI on weeds managed to give a good indication of final grain yields in maize crop. Indeed, grain yield showed a negative correlation with the NDVI and weed biomass (−0.39 and −0.5, respectively), confirming the well-known negative effect of weed competition on crop yield [8,20] and the potential of the NDVI to give an indication of weed and crop growth and productivity (depending on where, when and how we take this measurement).…”

“…In total, maize plants in plots subjected to herbicide treatments showed a higher grain yield than plants in untreated control plots (T1). Herbicide applications reduced the effect of weed infestation on the final grain yield of maize, while the efficacy of each treatment differed among fields [20]. In particular, the mixture nicosulfuron + rimsulfuron + mesotrione (T2) documented high efficacy on the crop yield of all fields, and the highest at Pyrgos1 and Pyrgos2 for both experimental years.…”

Enhancing Crop Yield Predictions with PEnsemble 4: IoT and ML-Driven for Precision Agriculture

“…The study explores the efficacy of 14 distinct ML algorithms in predicting the growth stage and productivity of maize. These algorithms encompass CatBoost regression [48], decision tree regression [49,50], ElasticNet regression [51], gradient boosting regression [52,53], Huber regression [54], K-Nearest Neighbors (KNN) regression [55], LASSO regression [56], linear regression [57], M estimators [58], passive aggressive regression, random forest (RF) regression [59], ridge regression, Support Vector Regression (SVR) [60], and XGBoost regression [61]. By employing this diverse range of algorithms, the authors aimed to optimize the accuracy and reliability of crop yield prediction in the context of precision agriculture.…”

“…Model 2 (decision tree regression) [49,50]: Selected to interpret the impact of different temporal features on crop yields, decision tree regression leverages its hierarchical structure to represent complex relationships within the data. [51]: Addressing multicollinearity and performing feature selection simultaneously, ElasticNet regression has proven crucial for highdimensional multi-temporal data.…”