Detection of Defoliation Injury in Peanut with Hyperspectral Proximal Remote Sensing

Precision estimation of winter wheat crop height and above-ground biomass using unmanned aerial vehicle imagery and oblique photoghraphy point cloud data

Introduction

Crop height and above-ground biomass (AGB) serve as crucial indicators for monitoring crop growth and estimating grain yield. Timely and accurate acquisition of wheat crop height and AGB data is paramount for guiding agricultural production. However, traditional data acquisition methods suffer from drawbacks such as time-consuming, laborious and destructive sampling.

Methods

The current approach to estimating AGB using unmanned aerial vehicles (UAVs) remote sensing relies solely on spectral data, resulting in low accuracy in estimation. This method fails to address the ill-posed inverse problem of mapping from two-dimensional to three-dimensional and issues related to spectral saturation. To overcome these challenges, RGB and multispectral sensors mounted on UAVs were employed to acquire spectral image data. The five-directional oblique photography technique was utilized to construct the three-dimensional point cloud for extracting crop height.

Results and Discussion

This study comparatively analyzed the potential of the mean method and the Accumulated Incremental Height (AIH) method in crop height extraction. Utilizing Vegetation Indices (VIs), AIH and their feature combinations, models including Random Forest Regression (RFR), eXtreme Gradient Boosting (XGBoost), Gradient Boosting Regression Trees (GBRT), Support Vector Regression (SVR) and Ridge Regression (RR) were constructed to estimate winter wheat AGB. The research results indicated that the AIH method performed well in crop height extraction, with minimal differences between 95% AIH and measured crop height values were observed across various growth stages of wheat, yielding R2 ranging from 0.768 to 0.784. Compared to individual features, the combination of multiple features significantly improved the model's estimate accuracy. The incorporation of AIH features helps alleviate the effects of spectral saturation. Coupling VIs with AIH features, the model's R2 increases from 0.694-0.885 with only VIs features to 0.728-0.925. In comparing the performance of five machine learning algorithms, it was discovered that models constructed based on decision trees were superior to other machine learning algorithms. Among them, the RFR algorithm performed optimally, with R2 ranging from 0.9 to 0.93.

Conclusion

In conclusion, leveraging multi-source remote sensing data from UAVs with machine learning algorithms overcomes the limitations of traditional crop monitoring methods, offering a technological reference for precision agriculture management and decision-making.

Sensor-Based Quantification of Peanut Disease Defoliation Using an Unmanned Aircraft System and Multispectral Imagery

Early leaf spot (Passalora arachidicola) and late leaf spot (Nothopassalora personata) are two of the most economically important foliar fungal diseases of peanut, often requiring seven to eight fungicide applications to protect against defoliation and yield loss. Rust (Puccinia arachidis) may also cause significant defoliation depending on season and location. Sensor technologies are increasingly being utilized to objectively monitor plant disease epidemics for research and supporting integrated management decisions. This study aimed to develop an algorithm to quantify peanut disease defoliation using multispectral imagery captured by an unmanned aircraft system. The algorithm combined the Green Normalized Difference Vegetation Index and the Modified Soil-Adjusted Vegetation Index and included calibration to site-specific peak canopy growth. Beta regression was used to train a model for percent net defoliation with observed visual estimations of the variety 'GA-06G' (0 to 95%) as the target and imagery as the predictor (train: pseudo-R2 = 0.71, test k-fold cross-validation: R2 = 0.84 and RMSE = 4.0%). The model performed well on new data from two field trials not included in model training that compared 25 (R2 = 0.79, RMSE = 3.7%) and seven (R2 = 0.87, RMSE = 9.4%) fungicide programs. This objective method of assessing mid-to-late season disease severity can be used to assist growers with harvest decisions and researchers with reproducible assessment of field experiments. This model will be integrated into future work with proximal ground sensors for pathogen identification and early season disease detection.[Formula: see text] Copyright © 2024 The Author(s). This is an open access article distributed under the CC BY 4.0 International license.

Negative effects on the development of Chrysodeixis includens and Spodoptera cosmioides fed by peanut plants inoculated with entomopathogenic fungi

Recent studies have shown that entomopathogenic fungi, as endophytes, can have beneficial effects on plants, protecting them from defoliating insects. The potential of endophytic association by entomopathogenic fungi with the peanut crop has been little explored. In our study, we conducted experiments by inoculation of peanut seeds through a soil drench method with nine strains/species of entomopathogenic fungi of the genera Metarhizium, Beauveria and Cordyceps, subsequently these plants were consumed by two larval pests, Chrysodeixis includens and Spodoptera cosmioides. The parameters of larval growth rates, mortality, foliar consumption and larval period were observed during the development of larvae. In addition, the endophytic capacity of these fungi in peanut plants and their persistence in soil were investigated. In two replicate greenhouse trials for each larva, peanut plants were inoculated with fungi by the soil-drench method. We evaluated the performance of C. includens and S. cosmioides feeding on inoculated peanut plants starting at the 2nd larval instar. The larval and pupal weights of C. includens and S. cosmioides were significantly different among the fungal treatment groups, where insects feeding on control plants exhibited higher larval and pupal weights than insects feeding on treated plants. The differences in larval period showed that Control larvae pupated faster than the larvae fed on fungal-inoculated plants, fungal treatments had a larval period of 3 to 5 days more than the control. The mortality rates of C. includens and S. cosmioides were significantly different among the fungal treatment groups, insects fed on Control plants exhibited higher survival than insects fed on fungal-inoculated plants. The persistence of all Metarhizium fungi was higher in the soil compared to other fungi, and only Metarhizium and B. bassiana IBCB215 emerged from the phyllosphere of peanut plants. Although the fungus Cordyceps presented the worst performance among the fungal treatments. Overall, our results demonstrate the negative effects on the development of C. includens and S. cosmioides that were fed on fungal-inoculated peanut plants, the best results recorded were for Metarhizium strains and the fungus B. bassiana IBCB215.

How does the digital transformation of agriculture affect the implementation of Integrated Pest Management?

Integrated pest management (IPM) has greatly influenced farming in the past decades. Even though it has been effective, its adoption has not been as large as anticipated. Operational issues regarding crop monitoring are among the reasons for the lack of adoption of the IPM philosophy because control decisions cannot be made unless the crop is effectively and constantly monitored. In this way, recent technologies can provide unique information about plants affected by insects. Such information can be very precise and timely, especially with the use of real-time data to allow decision-making for pest control that can prevent local infestation of insects from spreading to the whole field. Some of the digital tools that are commercially available for growers include drones, automated traps, and satellites. In the future, a variety of other technologies, such as autonomous robots, could be widely available. While the traditional IPM approach is generally carried out with control solutions being delivered throughout the whole field, new approaches involving digital technologies will need to consider adaptations in the concepts of economic thresholds, sampling, population forecast, injury identification, and ultimately the localized use of control tactics. Therefore, in this paper, we reviewed how the traditional IPM concepts could be adapted, considering this ongoing digital transformation in agriculture.

Effects of feeding injury from Popillia japonica (Coleoptera: Scarabaeidae) on soybean spectral reflectance and yield

Remote sensing has been shown to be a promising technology for the detection and monitoring of plant stresses including insect feeding. Popillia japonica Newman, is an invasive insect species in the United States, and a pest of concern to soybean, Glycine max (L.) Merr., in the upper Midwest. To investigate the effects of P. japonica feeding injury (i.e., defoliation) on soybean canopy spectral reflectance and yield, field trials with plots of caged soybean plants were established during the summers of 2020 and 2021. In each year, field-collected P. japonica adults were released into some of the caged plots, creating a gradient of infestation levels and resulting injury. Estimates of injury caused by P. japonica, ground-based hyperspectral readings, total yield, and yield components were obtained from the caged plots. Injury was greatest in the upper canopy of soybean in plots infested with P. japonica. Overall mean canopy injury (i.e., across lower, middle, and upper canopy) ranged from 0.23 to 6.26%, which is representative of injury levels observed in soybean fields in the Midwest United States. Feeding injury from P. japonica tended to reduce measures of soybean canopy reflectance in near infra-red wavelengths (~700 to 1000 nm). These results indicate that remote sensing has potential for detection of injury from P. japonica and could facilitate scouting for this pest. Effects of P. japonica injury on total yield were not observed, but a reduction in seed size was detected in one of the two years. The threat to soybean yield posed by P. japonica alone appears minimal, but this pest adds to the guild of other defoliating insects in soybean whose combined effects could threaten yield. The results of this research will guide refinement of management recommendations for this pest in soybean and hold relevance for other cropping systems.

Estimation of Above-Ground Biomass of Winter Wheat Based on Consumer-Grade Multi-Spectral UAV

One of the problems of optical remote sensing of crop above-ground biomass (AGB) is that vegetation indices (VIs) often saturate from the middle to late growth stages. This study focuses on combining VIs acquired by a consumer-grade multiple-spectral UAV and machine learning regression techniques to (i) determine the optimal time window for AGB estimation of winter wheat and to (ii) determine the optimal combination of multi-spectral VIs and regression algorithms. UAV-based multi-spectral data and manually measured AGB of winter wheat, under five nitrogen rates, were obtained from the jointing stage until 25 days after flowering in the growing season 2020/2021. Forty-four multi-spectral VIs were used in the linear regression (LR), partial least squares regression (PLSR), and random forest (RF) models in this study. Results of LR models showed that the heading stage was the most suitable stage for AGB prediction, with R2 values varying from 0.48 to 0.93. Three PLSR models based on different datasets performed differently in estimating AGB in the training dataset (R2 = 0.74~0.92, RMSE = 0.95~2.87 t/ha, MAE = 0.75~2.18 t/ha, and RPD = 2.00~3.67) and validation dataset (R2 = 0.50~0.75, RMSE = 1.56~2.57 t/ha, MAE = 1.44~2.05 t/ha, RPD = 1.45~1.89). Compared with PLSR models, the performance of the RF models was more stable in the prediction of AGB in the training dataset (R2 = 0.95~0.97, RMSE = 0.58~1.08 t/ha, MAE = 0.46~0.89 t/ha, and RPD = 3.95~6.35) and validation dataset (R2 = 0.83~0.93, RMSE = 0.93~2.34 t/ha, MAE = 0.72~2.01 t/ha, RPD = 1.36~3.79). Monitoring AGB prior to flowering was found to be more effective than post-flowering. Moreover, this study demonstrates that it is feasible to estimate AGB for multiple growth stages of winter wheat by combining the optimal VIs and PLSR and RF models, which overcomes the saturation problem of using individual VI-based linear regression models.

Monitoring Forest Health Using Hyperspectral Imagery: Does Feature Selection Improve the Performance of Machine-Learning Techniques?

This study analyzed highly correlated, feature-rich datasets from hyperspectral remote sensing data using multiple statistical and machine-learning methods. The effect of filter-based feature selection methods on predictive performance was compared. In addition, the effect of multiple expert-based and data-driven feature sets, derived from the reflectance data, was investigated. Defoliation of trees (%), derived from in situ measurements from fall 2016, was modeled as a function of reflectance. Variable importance was assessed using permutation-based feature importance. Overall, the support vector machine (SVM) outperformed other algorithms, such as random forest (RF), extreme gradient boosting (XGBoost), and lasso (L1) and ridge (L2) regressions by at least three percentage points. The combination of certain feature sets showed small increases in predictive performance, while no substantial differences between individual feature sets were observed. For some combinations of learners and feature sets, filter methods achieved better predictive performances than using no feature selection. Ensemble filters did not have a substantial impact on performance. The most important features were located around the red edge. Additional features in the near-infrared region (800–1000 nm) were also essential to achieve the overall best performances. Filter methods have the potential to be helpful in high-dimensional situations and are able to improve the interpretation of feature effects in fitted models, which is an essential constraint in environmental modeling studies. Nevertheless, more training data and replication in similar benchmarking studies are needed to be able to generalize the results.