Search

During the past few decades, a range of digital strategies for Nitrogen (N) management using various types of input data and recommendation frameworks have been developed. Despite much research, the benefits accrued from such technology have been equivocal. In this work, thirteen methods for mid-season N recommendations in cereal production systems were evaluated simultaneously, ranging from simple mass balance through to non-mechanistic approaches based on machine learning. To achieve this, an extensive field research program was implemented, comprising twenty-one N strip trials implemented in wheat and barley fields across Australia over four cropping seasons. A moving window regression approach was used to generate crop response functions to applied N and calculate economically optimal N rates along the length of the strips. The N recommendations made using various methods were assessed based on the error against the optimal rate and expected profitability. The root mean squared error of the recommendations ranged from 15 to 57 kg/ha. The best performing method was a data-driven empirical strategy in which a multivariate input to characterise field and season conditions was abundantly available and used to predict optimal N rates using machine learning. This was the only approach with potential to substantially outperform the existing farmer management, reducing the recommendation error from 42 to 15 kg/ha and improving profitability by up to A$47/ha. Despite being reliant on extensive historical databases, such a framework shows a promising pathway to drive production systems closer towards season- and site-specific economically optimum recommendations. Automated on-farm experimentation is a key enabler for building the necessary crop response databases to run empirical data-driven decision tools. [ABSTRACT FROM AUTHOR]

As farming practices become increasingly automated, the quantity of high resolution on-farm production information grows exponentially and so does the need for high-throughput computing solutions to aid management. High resolution (5 m) wheat yield forecasting is presented here using two machine learning approaches: (a) Bootstrapped Regression Trees (BRR) where predictions are pixel-wise and (b) Convolutional Neural Networks (CNN) where predictions use neighbouring pixels. This study focused on three aims. First, to compare the two approaches in a yield forecasting task that included publicly available data and on-farm gathered yield data. Second, to study any benefit of adding more layers of information in the modelling process, e.g. proximal soil sensing surveys. Third, to evaluate the value of including information from contiguous neighbouring fields in order to forecast within-field wheat yield at harvest. Results showed that BRR modelling using publicly available Sentinel data with the addition of local electromagnetic induction surveys or gamma radiometric surveys produced the best forecasts as determined by the classical performance metrics. The results from the CNN models improved with the addition of publicly available data from neighbouring fields and produced a spatial distribution pattern that most closely resembled the actual yield data. Within-field yield forecasting using machine learning techniques and publicly available data shows good potential, and this work suggests that the choice of yield forecasting methodology may depend on the type and extent of spatial data that is available for use in forecasting. [ABSTRACT FROM AUTHOR]

Background: Dysarthria after stroke is when speech intelligibility is impaired, and this occurs in half of all stroke survivors. Dysarthria often leads to social isolation, poor psychological well-being and can prevent return to work and social lives. Currently, a variety of outcome measures are used in clinical research and practice when monitoring recovery for people who have dysarthria. When research studies use different measures, it is impossible to compare results from trials and delays our understanding of effective clinical treatments. The aim of this study is to develop a core outcome set (COS) to agree what aspects of speech recovery should be measured for dysarthria after stroke (COS-Speech) in research and clinical practice. Methods: The COS-Speech study will include five steps: (1) development of a long list of possible outcome domains of speech that should be measured to guide the survey; (2) recruitment to the COS-Speech study of three key stakeholder groups in the UK and Australia: stroke survivors, communication researchers and speech and language therapists/pathologists; (3) two rounds of the Delphi survey process; (4) a consensus meeting to agree the speech outcomes to be measured and a follow-up consensus meeting to match existing instruments/measures (from parallel systematic review) to the agreed COS-Speech; (5) dissemination of COS-Speech. Discussion: There is currently no COS for dysarthria after stroke for research trials or clinical practice. The findings from this research study will be a minimum COS, for use in all dysarthria research studies and clinical practice looking at post-stroke recovery of speech. These findings will be widely disseminated using professional and patient networks, research and clinical forums as well as using a variety of academic papers, videos, accessible writing such as blogs and links on social media. Trial registration: COS-Speech is registered with the Core Outcome Measures in Effectiveness Trials (COMET) database, October 2021 https://www.comet-initiative.org/Studies/Details/1959. In addition, "A systematic review of the psychometric properties and clinical utility of instruments measuring dysarthria after stroke" will inform the consensus meeting to match measures to COS-Speech. The protocol for the systematic reviews registered with the International Prospective Register of Systematic Reviews. PROSPERO registration number: CRD42022302998. [ABSTRACT FROM AUTHOR]

Low-frequency repetitive transcranial magnetic stimulation (rTMS) has emerged as a potential tool for neurorehabilitation and remediation of language in chronic non-fluent aphasia post-stroke. Inhibitory (1 Hz) rTMS has been applied to homologous language sites to facilitate behavioural language changes. Improvements in picture-naming performance and speech output over time have been reported. Low-frequency (1 Hz) rTMS was applied to six real stimulation and six sham placebo patients for 20 min per day, for 10 days, and behavioural language outcome measures were taken at baseline (pre-stimulation) and 2 months post-stimulation. The findings demonstrate treatment-related changes observed in the stimulation group when compared to the placebo control group at 2 months post-stimulation on naming performance as well as other aspects of expressive language and auditory comprehension. These findings provide considerable evidence to support the theory of rTMS modulating mechanisms of transcallosal disinhibition in the aphasic brain and highlight the potential clinical applications for language rehabilitation post-stroke. Click for the corresponding questions to this CME article. [ABSTRACT FROM AUTHOR]