Please cite this article in press as: Elarab, M., et al., Estimating chlorophyll with thermal and broadband multispectral high resolution imagery from an unmanned aerial system using relevance vector machines for precision agriculture. Int. J. Appl. Earth Observ. Geoinf. (2015), http://dx. a b s t r a c tPrecision agriculture requires high-resolution information to enable greater precision in the management of inputs to production. Actionable information about crop and field status must be acquired at high spatial resolution and at a temporal frequency appropriate for timely responses. In this study, high spatial resolution imagery was obtained through the use of a small, unmanned aerial system called AggieAir TM . Simultaneously with the AggieAir flights, intensive ground sampling for plant chlorophyll was conducted at precisely determined locations. This study reports the application of a relevance vector machine coupled with cross validation and backward elimination to a dataset composed of reflectance from high-resolution multi-spectral imagery (VIS-NIR), thermal infrared imagery, and vegetative indices, in conjunction with in situ SPAD measurements from which chlorophyll concentrations were derived, to estimate chlorophyll concentration from remotely sensed data at 15-cm resolution. The results indicate that a relevance vector machine with a thin plate spline kernel type and kernel width of 5.4, having LAI, NDVI, thermal and red bands as the selected set of inputs, can be used to spatially estimate chlorophyll concentration with a root-mean-squared-error of 5.31 g cm −2 , efficiency of 0.76, and 9 relevance vectors.

No abstract

Spatial surface soil moisture can be an important indicator of crop conditions on farmland, but its continuous estimation remains challenging due to coarse spatial and temporal resolution of existing remotely-sensed products. Furthermore, while preceding research on soil moisture using remote sensing (surface energy balance, weather parameters, and vegetation indices) has demonstrated a relationship between these factors and soil moisture, practical continuous spatial quantification of the latter is still unavailable for use in water and agricultural management. In this study, a methodology is presented to estimate volumetric surface soil moisture by statistical selection from potential predictors that include vegetation indices and energy balance products derived from satellite (Landsat) imagery and weather data as identified in scientific literature. This methodology employs a statistical learning machine called a Relevance Vector Machine (RVM) to identify and relate the potential predictors to soil moisture by means of stratified cross-validation and forward variable selection. Surface soil moisture measurements from irrigated agricultural fields in Central Utah in the 2012 irrigation season were used, along with weather data, Landsat vegetation indices, and energy balance products. The methodology, data collection, processing, and estimation accuracy are presented and discussed.

No abstract

This research presents a model that simultaneously forecasts required water releases 1 and 2 days ahead from two reservoirs that are in series. In practice, multiple reservoir system operation is a difficult process that involves many decisions for real-time water resources management. The operator of the reservoirs has to release water from more than one reservoir taking into consideration different water requirements (irrigation, environmental issues, hydropower, recreation, etc.) in a timely manner. A model that forecasts the required real-time releases in advance from a multiple reservoir system could be an important tool to allow the operator of the reservoir system to make better-informed decisions for releases needed downstream. The model is developed in the form of a multivariate relevance vector machine (MVRVM) that is based on a sparse Bayesian regression model approach. With this Bayesian approach, a predictive confidence interval is obtained from the model that captures the uncertainty of both the model and the data. The model is applied to the multiple reservoir system located in the Lower Sevier River Basin near Delta, Utah. The results show that the model learns the input-output patterns with high accuracy. Computing multiple-time-ahead predictions in real-time would require a model which guarantees not only good prediction accuracy but also robustness with respect to future changes in the nature of the inputs data. A bootstrap analysis is used to guarantee good generalization ability and robustness of the MVRVM. Test results demonstrate good performance of predictions and statistics that indicate robust model generalization abilities. The MVRVM is compared in terms of performance and robustness with another multiple output model such as Artificial Neural Network (ANN). A. M. Ticlavilca (B) · M. McKee