Development of hay yield monitoring systems
Loading...
Authors
Meeting name
Sponsors
Date
Journal Title
Format
Thesis
Subject
Abstract
Precision agriculture (PA) technologies, such as GPS-guided tractors and unmanned aerial vehicles (UAVs), have increased farming efficiency, allowing precise input application and reducing waste. Precision agriculture enhances crop yield and quality, balancing economic and environmental interests. Simultaneously, hay production in agriculture, crucial for livestock during scarce pasture periods, benefits from these advancements. Its harvesting process, aimed at preserving nutritional value and preventing spoilage, enables large-scale storage for consistent livestock feeding. Additionally, hay production, adaptable to various climatic conditions and incorporating diverse grass and legume species, enhances soil health and aligns with sustainable agriculture principles. Previous research on using proximal and remote sensing for hay yield estimation has shown promise but faces several limitations. These include low accuracy in mixed species or low-density crops and in heterogeneous field conditions. Challenges also arise in selecting optimal data collection dates and dealing with ambient conditions like wind and dirt, which affect the accuracy of both proximal and remote sensing technologies. These limitations highlight the need for improved methods in hay yield estimation. This study aims to develop and evaluate hay yield estimation systems using remote and proximal sensing as an improvement over the conventional bale weight method. The focus is on enhancing spatial resolution for site-specific management, involving the use of LiDAR, ultrasonic sensors, and UAV-based remote sensing. It includes detailed analysis, data processing methodologies, predictive model evaluation, and key variable identification. The study is structured into chapters, each addressing a specific aspect of yield estimation, including preliminary remote sensing tests, machine learning applications using UAV imagery, and comparative analysis of proximal sensing technologies. All studies were conducted in a 35-ha field near Centralia, Missouri, involving the collection of ground-truth biomass data in a hay field having a mixture of timothy grass and red clover, proximal sensing data by ground based ultrasonic and LiDAR, and UAV-based remote sensing data. Ground-truth data was collected in 1-m2 quadrats and multiple descriptive statistics such as median, mean and quantile 90 percent were extracted for calibration and validation for all studies. The first study utilized various multispectral image vegetation indices (VIs) and regression models for biomass estimation. It evaluated the use of multispectral imaging systems, along with data collection and processing approaches. A multiple linear regression model was developed, using independent variables selected from candidate VIs and texture features, to predict hay biomass. Model performance was evaluated using measures like R2 and RMSE, and models including VIs and texture features provided R2 values from 0.31 to 0.68. Significant findings included correlations between VIs and dry mass and the effectiveness of texture features in improving model accuracy. While standard VIs showed substantial correlation with biomass, challenges like variable image resolution impacted accuracy. The second study used UAV-based remote sensing systems and machine learning models to estimate and map hay yield, employing a red-green-blue (RGB) camera for image acquisition. A random forest (RF) model was applied to estimate yield, after selecting predictive variables from VIs, texture features, color features, moisture content, and proportion of grass through recursive feature elimination (RFE). The highest accuracy model achieved R2 = 0.59, RMSE = 331 g/m^2, and MAE = 277 g/m^2 for wet hay mass estimation. This research provided insights into the selection of appropriate analysis methods for hay estimation using UAV imagery and showed the prospects for future research to apply these models to whole-field imagery for creating hay yield maps. Finally, the last study focused on comparing the effectiveness of ultrasonic and LiDAR sensors for estimating hay yield. The use of these sensors to measure plant height when mounted on a boom in front of a hay mower was evaluated, correlating these measurements with hay biomass. Data from the ultrasonic sensor, collected over a 3 m range and analyzed with machine learning models, provided the most accurate biomass estimates, with R2 values ranging from 0.31 to 0.52. Decision tree models were the most effective for use with data collected by these sensors. Results indicated that higher sensor data collection frequencies might improve prediction results.
Table of Contents
PubMed ID
Degree
Ph. D.