More Like this

1. Soybean maturity prediction using two‐dimensional contour plots from drone‐based time series imagery

   https://doi.org/10.1002/ppj2.70036  

   Kim, Bitgoeul; Blair, Samuel W; Jubery, Talukder Z; Sarkar, Soumik; Singh, Arti; Singh, Asheesh K; Ganapathysubramanian, Baskar (December 2025, The Plant Phenome Journal)

   Abstract Plant breeding programs require assessment and understanding of days to maturity for accurate selection and placement of entries in appropriate tests. Soybean [Glycine max(L.) Merr.] breeding programs, in the early stages of the breeding pipeline, assign relative maturity ratings to experimental varieties that indicate their suitable maturity zones. Traditionally, the estimation of maturity rating value has involved breeders manually inspecting fields and assessing maturity value visually. This approach relies heavily on expert judgment, making it subjective and demanding considerable time and effort. This study aimed to develop a machine learning (ML) model for evaluating soybean maturity using uncrewed aerial system (UAS)–based time series imagery. Images were captured at 3‐day intervals, beginning as the earliest varieties started maturing and continuing until the last varieties fully matured. The data collected for this experiment consisted of 22,043 plots collected across 3 years and represent relative maturity groups 1.6–3.9. We utilized contour plot images extracted from the time series UAS imagery as input for a neural network model. This contour plot approach encoded the temporal and spatial variation within each plot into a single image. A deep learning model was trained to utilize this contour plot to predict maturity ratings. This model demonstrates a significant improvement in accuracy and robustness, achieving up to 85% accuracy. The predictive model offers a scalable, objective, and efficient means of assessing crop maturity, enabling phenomics and ML approaches to reduce the reliance on manual inspection and subjective assessment, thereby saving time and resources in a breeding program. 

   more » « less
2. Classification and Feature Extraction for Hydraulic Structures Data Using Advanced CNN Architectures

   https://doi.org/10.1109/TransAI51903.2021.00032  

   Talafha, Sameerah; Wu, Di; Rekabdar, Banafsheh; Li, Ruopu; Wang, Guangxing (September 2021, 2021 Third International Conference on Transdisciplinary AI (TransAI))

   An efficient feature selection method can significantly boost results in classification problems. Despite ongoing improvement, hand-designed methods often fail to extract features capturing high- and mid-level representations at effective levels. In machine learning (Deep Learning), recent developments have improved upon these hand-designed methods by utilizing automatic extraction of features. Specifically, Convolutional Neural Networks (CNNs) are a highly successful technique for image classification which can automatically extract features, with ongoing learning and classification of these features. The purpose of this study is to detect hydraulic structures (i.e., bridges and culverts) that are important to overland flow modeling and environmental applications. The dataset used in this work is a relatively small dataset derived from 1-m LiDAR-derived Digital Elevation Models (DEMs) and National Agriculture Imagery Program (NAIP) aerial imagery. The classes for our experiment consist of two groups: the ones with a bridge/culvert being present are considered "True", and those without a bridge/culvert are considered "False". In this paper, we use advanced CNN techniques, including Siamese Neural Networks (SNNs), Capsule Networks (CapsNets), and Graph Convolutional Networks (GCNs), to classify samples with similar topographic and spectral characteristics, an objective which is challenging utilizing traditional machine learning techniques, such as Support Vector Machine (SVM), Gaussian Classifier (GC), and Gaussian Mixture Model (GMM). The advanced CNN-based approaches combined with data pre-processing techniques (e.g., data augmenting) produced superior results. These approaches provide efficient, cost-effective, and innovative solutions to the identification of hydraulic structures. 

   more » « less
3. Detecting intra-field variation in rice yield with UAV imagery and deep learning

   https://doi.org/10.3389/fpls.2022.716506  

   Bellis, E.; Hashem, A.; Causey, J; Runkle, B.R.; Moreno-Garcia, B.; Burns, B; Green, V.S.; Burcham, T.N.; Reba, M.L.; Huang, X. (March 2022, Frontiers in plant science)

   Unmanned aerial vehicles (UAVs) equipped with multispectral sensors offer high spatial and temporal resolution imagery for monitoring crop stress at early stages of development. Analysis of UAV-derived data with advanced machine learning models could improve real-time management in agricultural systems, but guidance for this integration is currently limited. Here we compare two deep learning-based strategies for early warning detection of crop stress, using multitemporal imagery throughout the growing season to predict field-scale yield in irrigated rice in eastern Arkansas. Both deep learning strategies showed improvements upon traditional statistical learning approaches including linear regression and gradient boosted decision trees. First, we explicitly accounted for variation across developmental stages using a 3D convolutional neural network (CNN) architecture that captures both spatial and temporal dimensions of UAV images from multiple time points throughout one growing season. 3D-CNNs achieved low prediction error on the test set, with a Root Mean Squared Error (RMSE) of 8.8% of the mean yield. For the second strategy, a 2D-CNN, we considered only spatial relationships among pixels for image features acquired during a single flyover. 2D-CNNs trained on images from a single day were most accurate when images were taken during booting stage or later, with RMSE ranging from 7.4 to 8.2% of the mean yield. A primary benefit of convolutional autoencoder-like models (based on analyses of prediction maps and feature importance) is the spatial denoising effect that corrects yield predictions for individual pixels based on the values of vegetation index and thermal features for nearby pixels. Our results highlight the promise of convolutional autoencoders for UAV-based yield prediction in rice. 

   more » « less
4. Detection of Individual Corn Crop and Canopy Delineation from Unmanned Aerial Vehicle Imagery

   https://doi.org/10.3390/rs16142679  

   Dorbu, Freda; Hashemi-Beni, Leila (July 2024, Remote Sensing)

   Precise monitoring of individual crop growth and health status is crucial for precision agriculture practices. However, traditional inspection methods are time-consuming, labor-intensive, prone to human error, and may not provide the comprehensive coverage required for the detailed analysis of crop variability across an entire field. This research addresses the need for efficient and high-resolution crop monitoring by leveraging Unmanned Aerial Vehicle (UAV) imagery and advanced computational techniques. The primary goal was to develop a methodology for the precise identification, extraction, and monitoring of individual corn crops throughout their growth cycle. This involved integrating UAV-derived data with image processing, computational geometry, and machine learning techniques. Bi-weekly UAV imagery was captured at altitudes of 40 m and 70 m from 30 April to 11 August, covering the entire growth cycle of the corn crop from planting to harvest. A time-series Canopy Height Model (CHM) was generated by analyzing the differences between the Digital Terrain Model (DTM) and the Digital Surface Model (DSM) derived from the UAV data. To ensure the accuracy of the elevation data, the DSM was validated against Ground Control Points (GCPs), adhering to standard practices in remote sensing data verification. Local spatial analysis and image processing techniques were employed to determine the local maximum height of each crop. Subsequently, a Voronoi data model was developed to delineate individual crop canopies, successfully identifying 13,000 out of 13,050 corn crops in the study area. To enhance accuracy in canopy size delineation, vegetation indices were incorporated into the Voronoi model segmentation, refining the initial canopy area estimates by eliminating interference from soil and shadows. The proposed methodology enables the precise estimation and monitoring of crop canopy size, height, biomass reduction, lodging, and stunted growth over time by incorporating advanced image processing techniques and integrating metrics for quantitative assessment of fields. Additionally, machine learning models were employed to determine relationships between the canopy sizes, crop height, and normalized difference vegetation index, with Polynomial Regression recording an R-squared of 11% compared to other models. This work contributes to the scientific community by demonstrating the potential of integrating UAV technology, computational geometry, and machine learning for accurate and efficient crop monitoring at the individual plant level. 

   more » « less
5. FloralArea: AI-powered algorithm for automated calculation of floral area from flower images to support plant and pollinator research

   https://doi.org/10.1371/journal.pone.0332165  

   Amoah, Edward I; White, Khayri; Patch, Harland M; Grozinger, Christina M (September 2025, PLOS One)

   Bouharroud, Rachid (Ed.)

   Floral area is a major predictor of the attractiveness of a flowering plant for pollinators, yet the measurement of floral area is time-consuming and inconsistent across studies. Here, we developed an AI-powered algorithm, FloralArea, to automate floral area measurement from an image. The FloralArea algorithm has two main components: an object segmentation module and an area estimation module. The object segmentation module extracts the pixels of flowers and the reference object in an image. The area estimation module predicts floral area based on the ratio between flower and reference object pixels. We fine-tuned two YOLOv8 segmentation models for flower and reference object segmentation. The flower segmentation model achieved moderate precision, recall, mAP0.5, and mAP0.5-0.95 of 0.794, 0.68, 0.741, and 0.455 on the test dataset, while the reference object model achieved an impressive performance of 0.907, 0.940, 0.933, and 0.832. We evaluated FloralArea using 75 images of flowering plants. We used ImageJ to calculate the actual floral area for all the images and compared them with the predicted floral area from FloralArea. The predicted floral area correlated well with the measured floral area with a coefficient of determination (R²) of 0.93 and a root mean square error of 20.58 cm². The FloralArea algorithm reduced the time it takes to calculate floral area from an image by 99.24% compared with traditional methods with image processing tools like ImageJ. By streamlining floral area estimation, the FloralArea algorithm provides a scalable, efficient, consistent, and accessible tool for researchers, particularly to aid in assessing plant attractiveness to different pollinator groups. 

   more » « less