Biomass estimation of spring wheat with machine learning methods using UAV-based multispectral imaging

Amorim, João Gustavo Atkinson; Schreiber, Lincoln Vinicius; Souza, Mirayr Raul Quadros de; Negreiros, Marcelo; Susin, Altamiro; Bredemeier, Christian; Trentin, Carolina; Vian, André Luis; Filho, Clódis de Oliveira Andrades; Doering, D.; Parraga, Adriane

doi:10.1080/01431161.2022.2107882

Cited by 9 publications

(7 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The smaller differences compared to those reported in some previous studies may be related to the relatively large dataset and the high number of predictors included. In contrast, RF was superior over SVM for biomass prediction in wheat [30,68] and over SVM for UAV-based biomass estimation [29]. However, as in the present study, few differences were reported for soybean GY prediction between RF, SVM, and a deep learning approach [32].…”

Section: The Comparison Of Machine Learning Algorithmscontrasting

confidence: 67%

“…The latter study [29] found better predictions using random forest (RF) than from stepwise multiple linear regression (MLR), support vector machine (SVM) regression, and extreme learning machine (ELM). Further studies confirmed the usefulness of RF in comparison to SVM for biomass estimation [30], to SVM and artificial neural networks (ANN) [31], and to SVM for UAV-based biomass estimation [29]. In contrast, differences between RF and SVM and deep learning were minor for soybean GY prediction [32].…”

Section: Introductionmentioning

confidence: 72%

See 1 more Smart Citation

UAV-Based Estimation of Grain Yield for Plant Breeding: Applied Strategies for Optimizing the Use of Sensors, Vegetation Indices, Growth Stages, and Machine Learning Algorithms

et al. 2022

View full text Add to dashboard Cite

Non-destructive in-season grain yield (GY) prediction would strongly facilitate the selection process in plant breeding but remains challenging for phenologically and morphologically diverse germplasm, notably under high-yielding conditions. In recent years, the application of drones (UAV) for spectral sensing has been established, but data acquisition and data processing have to be further improved with respect to efficiency and reliability. Therefore, this study evaluates the selection of measurement dates, sensors, and spectral parameters, as well as machine learning algorithms. Multispectral and RGB data were collected during all major growth stages in winter wheat trials and tested for GY prediction using six machine-learning algorithms. Trials were conducted in 2020 and 2021 in two locations in the southeast and eastern areas of Germany. In most cases, the milk ripeness stage was the most reliable growth stage for GY prediction from individual measurement dates, but the maximum prediction accuracies differed substantially between drought-affected trials in 2020 (R2 = 0.81 and R2 = 0.68 in both locations, respectively), and the wetter, pathogen-affected conditions in 2021 (R2 = 0.30 and R2 = 0.29). The combination of data from multiple dates improved the prediction (maximum R2 = 0.85, 0.81, 0.61, and 0.44 in the four-year*location combinations, respectively). Among the spectral parameters under investigation, the best RGB-based indices achieved similar predictions as the best multispectral indices, while the differences between algorithms were comparably small. However, support vector machine, together with random forest and gradient boosting machine, performed better than partial least squares, ridge, and multiple linear regression. The results indicate useful GY predictions in sparser canopies, whereas further improvements are required in dense canopies with counteracting effects of pathogens. Efforts for multiple measurements were more rewarding than enhanced spectral information (multispectral versus RGB).

show abstract

Section: The Comparison Of Machine Learning Algorithmscontrasting

confidence: 67%

Section: Introductionmentioning

confidence: 72%

UAV-Based Estimation of Grain Yield for Plant Breeding: Applied Strategies for Optimizing the Use of Sensors, Vegetation Indices, Growth Stages, and Machine Learning Algorithms

et al. 2022

View full text Add to dashboard Cite

show abstract

“…More spectral traits should be tested, as well as more machine learning algorithms. Thus, random forest was recommended in a number of studies [35][36][37], notably for its ability to handle heterogeneous data. This aspect might be more relevant in across-trials compared to within-trials models, in which prediction accuracies had been similar, but training time significantly higher [19].…”

Section: Limitations and Outlookmentioning

confidence: 99%

The Transferability of Spectral Grain Yield Prediction in Wheat Breeding across Years and Trial Locations

Prey

Ramgraber

Seidl-Schulz³

et al. 2023

Sensors

View full text Add to dashboard Cite

Grain yield (GY) prediction based on non-destructive UAV-based spectral sensing could make screening of large field trials more efficient and objective. However, the transfer of models remains challenging, and is affected by location, year-dependent weather conditions and measurement dates. Therefore, this study evaluates GY modelling across years and locations, considering the effect of measurement dates within years. Based on a previous study, we used a normalized difference red edge (NDRE1) index with PLS (partial least squares) regression, trained and tested with the data of individual dates and date combinations, respectively. While strong differences in model performance were observed between test datasets, i.e., different trials, as well as between measurement dates, the effect of the train datasets was comparably small. Generally, within-trials models achieved better predictions (max. R2 = 0.27–0.81), but R2-values for the best across-trials models were lower only by 0.03–0.13. Within train and test datasets, measurement dates had a strong influence on model performance. While measurements during flowering and early milk ripeness were confirmed for within- and across-trials models, later dates were less useful for across-trials models. For most test sets, multi-date models revealed to improve predictions compared to individual-date models.

show abstract

“…The red band, ranging from 690 to 720 nanometers, is the range that predominates the absorption by chlorophyll, while good relationships are found in the near-infrared wavelengths ranging from 760 to 800 nanometers, indicating high reflectance [35]. In beans, a reflectance peak starts near 490 nanometers and increases until 550 nanometers, then drops sharply and records lower reflectance between 665 and 680 nanometers [39].…”

Section: Resultsmentioning

confidence: 99%

Performance of Vegetation Indices to Estimate Green Biomass Accumulation in Common Bean

et al. 2023

View full text Add to dashboard Cite

Remote sensing technology applied to agricultural crops has emerged as an efficient tool to speed up the data acquisition process in decision-making. In this study, we aimed to evaluate the performance of the Normalized Difference Vegetation Index (NDVI) and the Normalized Difference Red Edge (NDRE) in estimating biomass accumulation in common bean crops. The research was conducted at the Federal University of Lavras, where the ANFC 9 cultivar was used in an area of approximately seven hectares, in a second crop, in 2022. A total of 31 georeferenced points spaced at 50 m were chosen to evaluate height, width and green biomass, with collections on days 15, 27, 36, 58, 62 and 76 of the crop cycle. The images used in the study were obtained from the PlanetScope CubeSat satellite, with a spatial resolution of 3 m. The data obtained were subjected to a Pearson correlation (R) test and multiple linear regression analysis. The green biomass variable was significantly correlated with plant height and width. The NDVI performed better than the NDRE, with higher values observed at 62 Days After Sowing (DAS). The model that integrates the parameters of height, width and NDVI was the one that presented the best estimate for green biomass in the common bean crop. The M1 model showed the best performance to estimate green biomass during the initial stage of the crop, at 15, 27 and 36 DAS (R2 = 0.93). These results suggest that remote sensing technology can be effectively applied to assess biomass accumulation in common bean crops and provide accurate data for decision-makers.

show abstract

Biomass estimation of spring wheat with machine learning methods using UAV-based multispectral imaging

Cited by 9 publications

References 27 publications

UAV-Based Estimation of Grain Yield for Plant Breeding: Applied Strategies for Optimizing the Use of Sensors, Vegetation Indices, Growth Stages, and Machine Learning Algorithms

UAV-Based Estimation of Grain Yield for Plant Breeding: Applied Strategies for Optimizing the Use of Sensors, Vegetation Indices, Growth Stages, and Machine Learning Algorithms

The Transferability of Spectral Grain Yield Prediction in Wheat Breeding across Years and Trial Locations

Performance of Vegetation Indices to Estimate Green Biomass Accumulation in Common Bean

Contact Info

Product

Resources

About