Optimal Hyperspectral Characteristics Determination for Winter Wheat Yield Prediction

Development of a vegetation canopy reflectance sensor and its diurnal applicability under clear sky conditions

The spectral reflectance provides valuable information regarding vegetation growth and plays an important role in agriculture, forestry, and grassland management. In this study, a small, portable vegetation canopy reflectance (VCR) sensor that can operate throughout the day was developed. The sensor includes two optical bands at 710 nm and 870 nm, with the light separated by filters, and has a field of view of 28°. It is powered by two 14500 rechargeable batteries and uses Wi-Fi for data transmission. The calibration of the sensor was performed using an integrating sphere, and a solar altitude correction model was constructed. The sensor's accuracy was validated using a standard reflectance gray scale board. The results indicate that the root mean square error (RMSE) and mean absolute error (MAE) at 710 nm were 1.07% and 0.63%, respectively, while those at 870 nm were 0.94% and 0.50%, respectively. Vegetation at 14 sites was measured using both the VCR sensor and an Analytical Spectral Devices (ASD) spectroradiometer at nearly the same time for each site. The results show that the reflectance values measured by both devices were closely aligned. Measurements of Bermuda grass vegetation on clear days revealed that the intra-day reflectance range at 710 nm narrowed from 12.3-19.2% before solar altitude correction to 11.1-13.4% after correction, and the coefficient of variation (CV) decreased from 10.86% to 2.93%. Similarly, at 870 nm, the intra-day reflectance range decreased from 41.6-60.3% to 39.0-42.0%, and the CV decreased from 9.69% to 1.53%. In summary, this study offers a fundamental tool for monitoring vegetation canopy reflectance in the field, which is crucial for advancing high-quality agricultural, grassland, and forest management practices.

Crop yield prediction in agriculture: A comprehensive review of machine learning and deep learning approaches, with insights for future research and sustainability

The agriculture sector is confronted with numerous challenges in the quest for accurate crop yield estimation, which is essential for efficient resource management and mitigating food scarcity in a rapidly growing global population. This research paper delves into the application of advanced Artificial Intelligence (AI) techniques to enhance crop yield estimation in the context of diverse agricultural challenges. Through a systematic literature review and analysis of relevant studies, this paper explores the role of AI methods, such as Machine Learning (ML) and Deep Learning (DL), in addressing the complexities posed by geographical variations, crop diversity, and cultivation areas. The review identifies a wealth of AI-powered solutions employed in crop yield prediction, emphasizing the importance of precise environmental and agricultural data. Key factors contributing to accurate estimation include temperature, rainfall, soil type, humidity, and various vegetation indices, such as NDVI, EVI, LAI, and NDWI. The research paper also examines the algorithms frequently utilized in the machine learning domain, including Random Forest (RF), Artificial Neural Networks (ANN), and Support Vector Machine (SVM). In the realm of deep learning, Convolutional Neural Networks (CNN), Long-Short Term Memory (LSTM), and Deep Neural Networks (DNN) emerge as promising candidates. The findings of this study shed light on the transformative potential of advanced AI techniques in improving crop yield estimation accuracy, ultimately enhancing agricultural planning and resource management. By addressing the challenges posed by geographical diversity, crop heterogeneity, and changing environmental conditions, AI-driven models offer new avenues for sustainable agriculture in an ever-evolving world. This research paper provides valuable insights and directions for future studies, highlighting the critical role of AI in ensuring food security and sustainability in agriculture.

Classification of major species in the sericite-Artemisia desert grassland using hyperspectral images and spectral feature identification

Background

The species composition of and changes in grassland communities are important indices for inferring the number, quality and community succession of grasslands, and accurate monitoring is the foundation for evaluating, protecting, and utilizing grassland resources. Remote sensing technology provides a reliable and powerful approach for measuring regional terrain information, and the identification of grassland species by remote sensing will improve the quality and effectiveness of grassland monitoring.

Methods

Ground hyperspectral images of a sericite-Artemisia desert grassland in different seasons were obtained with a Soc710 VP imaging spectrometer. First-order differential processing was used to calculate the characteristic parameters. Analysis of variance was used to extract the main species, namely, Seriphidium transiliense (Poljak), Ceratocarpus arenarius L., Petrosimonia sibirica (Pall), bare land and the spectral characteristic parameters and vegetation indices in different seasons. On this basis, Fisher discriminant analysis was used to divide the samples into a training set and a test set at a ratio of 7:3. The spectral characteristic parameters and vegetation indices were used to identify the three main plants and bare land.

Results

The selection of parameters with significant differences (P < 0.05) between the recognition objects effectively distinguished different land features, and the identification parameters also differed due to differences in growth period and species. The overall accuracy of the recognition model established by the vegetation index decreased in the following order: June (98.87%) > September (91.53%) > April (90.37%). The overall accuracy of the recognition model established by the feature parameters decreased in the following order: September (89.77%) > June (88.48%) > April (85.98%).

Conclusions

The recognition models based on vegetation indices in different months are superior to those based on feature parameters, with overall accuracies ranging from 1.76% to 9.40% higher. Based on hyperspectral image data, the use of vegetation indices as identification parameters can enable the identification of the main plants in sericite-Artemisia desert grassland, providing a basis for further quantitative classification of the species in community images.

UAV Multisensory Data Fusion and Multi-Task Deep Learning for High-Throughput Maize Phenotyping

Recent advances in unmanned aerial vehicles (UAV), mini and mobile sensors, and GeoAI (a blend of geospatial and artificial intelligence (AI) research) are the main highlights among agricultural innovations to improve crop productivity and thus secure vulnerable food systems. This study investigated the versatility of UAV-borne multisensory data fusion within a framework of multi-task deep learning for high-throughput phenotyping in maize. UAVs equipped with a set of miniaturized sensors including hyperspectral, thermal, and LiDAR were collected in an experimental corn field in Urbana, IL, USA during the growing season. A full suite of eight phenotypes was in situ measured at the end of the season for ground truth data, specifically, dry stalk biomass, cob biomass, dry grain yield, harvest index, grain nitrogen utilization efficiency (Grain NutE), grain nitrogen content, total plant nitrogen content, and grain density. After being funneled through a series of radiometric calibrations and geo-corrections, the aerial data were analytically processed in three primary approaches. First, an extended version normalized difference spectral index (NDSI) served as a simple arithmetic combination of different data modalities to explore the correlation degree with maize phenotypes. The extended NDSI analysis revealed the NIR spectra (750-1000 nm) alone in a strong relation with all of eight maize traits. Second, a fusion of vegetation indices, structural indices, and thermal index selectively handcrafted from each data modality was fed to classical machine learning regressors, Support Vector Machine (SVM) and Random Forest (RF). The prediction performance varied from phenotype to phenotype, ranging from R² = 0.34 for grain density up to R² = 0.85 for both grain nitrogen content and total plant nitrogen content. Further, a fusion of hyperspectral and LiDAR data completely exceeded limitations of single data modality, especially addressing the vegetation saturation effect occurring in optical remote sensing. Third, a multi-task deep convolutional neural network (CNN) was customized to take a raw imagery data fusion of hyperspectral, thermal, and LiDAR for multi-predictions of maize traits at a time. The multi-task deep learning performed predictions comparably, if not better in some traits, with the mono-task deep learning and machine learning regressors. Data augmentation used for the deep learning models boosted the prediction accuracy, which helps to alleviate the intrinsic limitation of a small sample size and unbalanced sample classes in remote sensing research. Theoretical and practical implications to plant breeders and crop growers were also made explicit during discussions in the studies.

Continuing progress in the field of two-dimensional correlation spectroscopy (2D-COS), part II. Recent noteworthy developments

This comprehensive survey review compiles noteworthy developments and new concepts of two-dimensional correlation spectroscopy (2D-COS) for the last two years. It covers review articles, books, proceedings, and numerous research papers published on 2D-COS, as well as patent and publication trends. 2D-COS continues to evolve and grow with new significant developments and versatile applications in diverse scientific fields. The healthy, vigorous, and diverse progress of 2D-COS studies in many fields strongly confirms that it is well accepted as a powerful analytical technique to provide an in-depth understanding of systems of interest.

Continuing progress in the field of two-dimensional correlation spectroscopy (2D-COS): Part III. Versatile applications

In this review, the comprehensive summary of two-dimensional correlation spectroscopy (2D-COS) for the last two years is covered. The remarkable applications of 2D-COS in diverse fields using many types of probes and perturbations for the last two years are highlighted. IR spectroscopy is still the most popular probe in 2D-COS during the last two years. Applications in fluorescence and Raman spectroscopy are also very popularly used. In the external perturbations applied in 2D-COS, variations in concentration, pH, and relative compositions are dramatically increased during the last two years. Temperature is still the most used effect, but it is slightly decreased compared to two years ago. 2D-COS has been applied to diverse systems, such as environments, natural products, polymers, food, proteins and peptides, solutions, mixtures, nano materials, pharmaceuticals, and others. Especially, biological and environmental applications have significantly emerged. This survey review paper shows that 2D-COS is an actively evolving and expanding field.

A Systematic Literature Review on Crop Yield Prediction with Deep Learning and Remote Sensing

Deep learning has emerged as a potential tool for crop yield prediction, allowing the model to automatically extract features and learn from the datasets. Meanwhile, smart farming technology enables the farmers to achieve maximum crop yield by extracting essential parameters of crop growth. This systematic literature review highlights the existing research gaps in a particular area of deep learning methodologies and guides us in analyzing the impact of vegetation indices and environmental factors on crop yield. To achieve the aims of this study, prior studies from 2012 to 2022 from various databases are collected and analyzed. The study focuses on the advantages of using deep learning in crop yield prediction, the suitable remote sensing technology based on the data acquisition requirements, and the various features that influence crop yield prediction. This study finds that Long Short-Term Memory (LSTM) and Convolutional Neural Networks (CNN) are the most widely used deep learning approaches for crop yield prediction. The commonly used remote sensing technology is satellite remote sensing technology—in particular, the use of the Moderate-Resolution Imaging Spectroradiometer (MODIS). Findings show that vegetation indices are the most used feature for crop yield prediction. However, it is also observed that the most used features in the literature do not always work for all the approaches. The main challenges of using deep learning approaches and remote sensing for crop yield prediction are how to improve the working model for better accuracy, the practical implication of the model for providing accurate information about crop yield to agriculturalists, growers, and policymakers, and the issue with the black box property.

Winter Wheat Yield Estimation Based on Optimal Weighted Vegetation Index and BHT-ARIMA Model

This study aims to use remote sensing (RS) time-series data to explore the intrinsic relationship between crop growth and yield formation at different fertility stages and construct a high-precision winter wheat yield estimation model applicable to short time-series RS data. Sentinel-2 images were acquired in this study at six key phenological stages (rejuvenation stage, rising stage, jointing stage, heading stage, filling stage, filling-maturity stage) of winter wheat growth, and various vegetation indexes (VIs) at different fertility stages were calculated. Based on the characteristics of yield data continuity, the RReliefF algorithm was introduced to filter the optimal vegetation index combinations suitable for the yield estimation of winter wheat for all fertility stages. The Absolutely Objective Improved Analytic Hierarchy Process (AOIAHP) was innovatively proposed to determine the proportional contribution of crop growth to yield formation in six different phenological stages. The selected VIs consisting of MTCI(RE2), EVI, REP, MTCI(RE1), RECI(RE1), NDVI(RE1), NDVI(RE3), NDVI(RE2), NDVI, and MSAVI were then fused with the weights of different fertility periods to obtain time-series weighted data. For the characteristics of short time length and a small number of sequences of RS time-series data in yield estimation, this study applied the multiplexed delayed embedding transformation (MDT) technique to realize the data augmentation of the original short time series. Tucker decomposition was performed on the block Hankel tensor (BHT) obtained after MDT enhancement, and the core tensor was extracted while preserving the intrinsic connection of the time-series data. Finally, the resulting multidimensional core tensor was trained with the Autoregressive Integrated Moving Average (ARIMA) model to obtain the BHT-ARIMA model for wheat yield estimation. Compared to the performance of the BHT-ARIMA model with unweighted time-series data as input, the weighted time-series input significantly improves yield estimation accuracy. The coefficients of determination (R2) were improved from 0.325 to 0.583. The root mean square error (RMSE) decreased from 492.990 to 323.637 kg/ha, the mean absolute error (MAE) dropped from 350.625 to 255.954, and the mean absolute percentage error (MAPE) decreased from 4.332% to 3.186%. Besides, BHT-ARMA and BHT-CNN models were also used to compare with BHT-ARIMA. The results indicated that the BHT-ARIMA model still had the best yield prediction accuracy. The proposed method of this study will provide fast and accurate guidance for crop yield estimation and will be of great value for the processing and application of time-series RS data.

The Classification Performance and Mechanism of Machine Learning Algorithms in Winter Wheat Mapping Using Sentinel-2 10 m Resolution Imagery

Machine learning algorithms are crucial for crop identification and mapping. However, many works only focus on the identification results of these algorithms, but pay less attention to their classification performance and mechanism. In this paper, based on Google Earth Engine (GEE), Sentinel-2 10 m resolution images during a specific phenological period of winter wheat were obtained. Then, support vector machine (SVM), random forest (RF), and classification and regression tree (CART) machine learning algorithms were employed to identify and map winter wheat in a large-scale area. The hyperparameters of the three machine learning algorithms were tuned by grid search and the 5-fold cross-validation method. The classification performance of the three machine learning algorithms were compared, the results of which demonstrate that SVM achieves best performance in identifying winter wheat, and its overall accuracy (OA), user’s accuracy (UA), producer’s accuracy (PA), and kappa coefficient (Kappa) are 0.94, 0.95, 0.95, and 0.92, respectively. Moreover, 50 various combinations of training and validation sets were used to analyze the generalization ability of the algorithms, and the results show that the average OA of SVM, RF, and CART are 0.93, 0.92, and 0.88, respectively, thus indicating that SVM and RF are more robust than CART. To further explore the sensitivity of SVM, RF, and CART to variations of the algorithm parameters—namely, (C and gamma), (tree and split), and (maxD and minSP)—we employed the grid search method to iterate these parameters, respectively, and to analyze the effect of these parameters on the accuracy scores and classification residuals. It was found that with the change of (C and gamma) in (0.01~1000), SVM’s maximum variation of accuracy score is up to 0.63, and the maximum variation of residuals is 76,215 km2. We concluded that SVM is sensitive to the parameters (C and gamma) and presents a positive correlation. When the parameters (tree and split) change between (100~600) and (1~6), respectively, the RF’s maximum variation of accuracy score is 0.08, and the maximum variation of residuals is 1157 km2, indicating that RF is low in sensitivity toward the parameters (tree and split). When the parameters (maxD and minSP) are between (10~60), the maximum accuracy change value is 0.06, and the maximum variation of residuals is 6943 km2. Therefore, compared to RF, CART is sensitive to the parameters (maxD and minSP) and has poor robustness. In general, under the conditions of the hyperparameters, SVM and RF exhibit optimal classification performance, while CART has relatively inferior performance. Meanwhile, SVM, RF, and CART have different sensitivities toward the algorithm parameters; that is, SVM and CART are more sensitive to the algorithm parameters, while RF has low sensitivity toward changes in the algorithm parameters. The different parameters cause great changes in the accuracy scores and residuals, so it is necessary to determine the algorithm hyperparameters. Generally, default parameters can be used to achieve crop classification, but we recommend the enumeration method, similar to grid search, as a practical way to improve the classification performance of the algorithm if the best classification effect is expected.

Combining Multi-Source Data and Machine Learning Approaches to Predict Winter Wheat Yield in the Conterminous United States

Winter wheat (Triticum aestivum L.) is one of the most important cereal crops, supplying essential food for the world population. Because the United States is a major producer and exporter of wheat to the world market, accurate and timely forecasting of wheat yield in the United States (U.S.) is fundamental to national crop management as well as global food security. Previous studies mainly have focused on developing empirical models using only satellite remote sensing images, while other yield determinants have not yet been adequately explored. In addition, these models are based on traditional statistical regression algorithms, while more advanced machine learning approaches have not been explored. This study used advanced machine learning algorithms to establish within-season yield prediction models for winter wheat using multi-source data to address these issues. Specifically, yield driving factors were extracted from four different data sources, including satellite images, climate data, soil maps, and historical yield records. Subsequently, two linear regression methods, including ordinary least square (OLS) and least absolute shrinkage and selection operator (LASSO), and four well-known machine learning methods, including support vector machine (SVM), random forest (RF), Adaptive Boosting (AdaBoost), and deep neural network (DNN), were applied and compared for estimating the county-level winter wheat yield in the Conterminous United States (CONUS) within the growing season. Our models were trained on data from 2008 to 2016 and evaluated on data from 2017 and 2018, with the results demonstrating that the machine learning approaches performed better than the linear regression models, with the best performance being achieved using the AdaBoost model (R2 = 0.86, RMSE = 0.51 t/ha, MAE = 0.39 t/ha). Additionally, the results showed that combining data from multiple sources outperformed single source satellite data, with the highest accuracy being obtained when the four data sources were all considered in the model development. Finally, the prediction accuracy was also evaluated against timeliness within the growing season, with reliable predictions (R2 > 0.84) being able to be achieved 2.5 months before the harvest when the multi-source data were combined.

Development of Optimized Phenomic Predictors for Efficient Plant Breeding Decisions Using Phenomic-Assisted Selection in Soybean

The rate of advancement made in phenomic-assisted breeding methodologies has lagged those of genomic-assisted techniques, which is now a critical component of mainstream cultivar development pipelines. However, advancements made in phenotyping technologies have empowered plant scientists with affordable high-dimensional datasets to optimize the operational efficiencies of breeding programs. Phenomic and seed yield data was collected across six environments for a panel of 292 soybean accessions with varying genetic improvements. Random forest, a machine learning (ML) algorithm, was used to map complex relationships between phenomic traits and seed yield and prediction performance assessed using two cross-validation (CV) scenarios consistent with breeding challenges. To develop a prescriptive sensor package for future high-throughput phenotyping deployment to meet breeding objectives, feature importance in tandem with a genetic algorithm (GA) technique allowed selection of a subset of phenotypic traits, specifically optimal wavebands. The results illuminated the capability of fusing ML and optimization techniques to identify a suite of in-season phenomic traits that will allow breeding programs to decrease the dependence on resource-intensive end-season phenotyping (e.g., seed yield harvest). While we illustrate with soybean, this study establishes a template for deploying multitrait phenomic prediction that is easily amendable to any crop species and any breeding objective.