Cotton significantly contributes to global agriculture and provides livelihoods for approximately 100 million farmers in 80 countries. Therefore, new approaches are needed to better inform producers, in near-real time, for optimising crop management practices, increasing profitability and sustainability. Here, we investigated the potential of proximal sensing metrics, derived from multispectral and thermal bands onboard an Unmanned Aerial Vehicles (UAVs), to estimate variability in cotton production due to different agronomic practices. We employed three main approaches, including (i) multilinear regression (MR), (ii) random forest (RF) and (iii) partial least square (PLS). All methods showed significantly strong relationship with lint yield. Specifically, the MR approach explained around 88% (R2= 0.88, RMSE = 322 kg/ha) of the variance in final yield across all plots. Further research is currently underway to explore the ability of multi-temporal, hyperspectral and radiative transfer models (RTM) to understand variability across different phenological stages in cotton management.

The classical binary hypothesis testing problem is revisited. We notice that when one of the hypotheses is composite, there is an inherent difficulty in defining an optimality criterion that is both informative and well-justified. For testing in the simple normal location problem (that is, testing for the mean of multivariate Gaussians), we overcome the difficulty as follows. In this problem there exists a natural “hardness” order between parameters as for different parameters the error-probabilities curves (when the parameter is known) are either identical, or one dominates the other. We can thus define minimax performance as the worst-case among parameters which are below some hardness level. Fortunately, there exists a universal minimax test, in the sense that it is minimax for all hardness levels simultaneously. Under this criterion we also find the optimal test for composite hypothesis testing with training data. THIS criterion extends to the wide class of local asymptotic normal models, in an asymptotic sense where the approximation of the error probabilities is additive. Since we have the asymptotically optimal tests for composite hypothesis testing with and without training data, we quantify the loss of universality and gain of training data for these models.

The discontent over the limited capability of Web services to reflect the organizationpsilas business model, and efficiently adhere to business strategies and requirements, caused a shift in business thinking. As a result, the enterprise has been recognizing the need for a more generalized model for services. This trend introduced a more abstracted notion of a service: a ldquometa-servicerdquo that can better explain business imperatives, foster business reuse, reduce time-to-market, and encourage asset consolidation across the enterprise. The recently published book which is also the base for this discussion: ldquoservice-oriented modeling: service analysis, design, and architecturerdquo provides answers to these organizational concerns.

(London)