- Dahlhaus, Peter, MacLeod, Andrew, Robinson, Nathan
- Authors: Dahlhaus, Peter , MacLeod, Andrew , Robinson, Nathan
- Type: Text , Dataset
- Full Text: false
- Description: DSM is a collaborative workspace for researchers working on digital soil mapping in Australia. This workspace is the initiative of the Advisory Group on Digital Soil Assessment, a working group of the National Committee on Soil & Terrain. The website is part of an interoperable web-GIS maintained by the Centre for eResearch and Digital Innovation (CeRDI) at Federation University Australia (FedUni). The International Union of Soil Sciences Digital Soil Mapping Working Group defines DSM as "creation and the population of a geographically referenced soil database, generated at a given resolution by using field and laboratory observation methods coupled with environmental data through quantitative relationships." Digital Soil Mapping (DSM) utilises numerical methods and information technologies to produce predictive maps of soil types and their properties. DSM relies on traditional field mapping, observations and laboratory analyses for soil data but also utilises spatial models of landscape terrain and remotely-sensed properties. Typically numerical methods such as interpolation algorithms and data mining are used to create the maps. OzDSM in collaboration with CeRDI is developing a digital soil mapping tool, and a demonstrator version is displayed on the site. A range of data is included, such as nutrient budgets and soil pH, and with extra data available for the Corangamite Catchment Management Authority region including landslides, erosion and salinity.
Online Farm Trials (OFT) – the past, present and future
- Robinson, Nathan, Dahlhaus, Peter, Feely, Paul, Light, Kate, MacLeod, Andrew
- Authors: Robinson, Nathan , Dahlhaus, Peter , Feely, Paul , Light, Kate , MacLeod, Andrew
- Type: Text , Conference paper
- Relation: Proceedings of the 19th Australian Society of Agronomy Conference,25-29 August 2019, Wagga Wagga, NSW, Australia
- Full Text:
- Reviewed:
- Description: Online Farm Trials (OFT) (www.farmtrials.com.au) is a free web-based resource and trial discovery system that contains more than 7,100 trials from 76 different organisations from across Australia. Since its inception in 2013, OFT has developed via a collaborative approach with grower groups, research organisations, agricultural experts and grains industry organisations. This ensures the outcomes are highly relevant, practical and beneficial for growers. Users can view, analyse and export grains research data as well as compare trials based upon historical, geographic and crop-specific search filters. Current developments include seasonally relevant collections of trials to highlight priority topics and aid on-farm decision making. To meet the future needs of industry stakeholders, system developments are planned to include expanded trial research information access, foster innovation through publishing and promoting active trials and enhance trial data standards and quality. **Please note that there are multiple Federation University authors for this article, including the name of the first 5 and also including “Rob Milne, Julie Parker, Helen Thompson, Judi Walters and Ben Wills" is provided in this record**
- Authors: Robinson, Nathan , Dahlhaus, Peter , Feely, Paul , Light, Kate , MacLeod, Andrew
- Type: Text , Conference paper
- Relation: Proceedings of the 19th Australian Society of Agronomy Conference,25-29 August 2019, Wagga Wagga, NSW, Australia
- Full Text:
- Reviewed:
- Description: Online Farm Trials (OFT) (www.farmtrials.com.au) is a free web-based resource and trial discovery system that contains more than 7,100 trials from 76 different organisations from across Australia. Since its inception in 2013, OFT has developed via a collaborative approach with grower groups, research organisations, agricultural experts and grains industry organisations. This ensures the outcomes are highly relevant, practical and beneficial for growers. Users can view, analyse and export grains research data as well as compare trials based upon historical, geographic and crop-specific search filters. Current developments include seasonally relevant collections of trials to highlight priority topics and aid on-farm decision making. To meet the future needs of industry stakeholders, system developments are planned to include expanded trial research information access, foster innovation through publishing and promoting active trials and enhance trial data standards and quality. **Please note that there are multiple Federation University authors for this article, including the name of the first 5 and also including “Rob Milne, Julie Parker, Helen Thompson, Judi Walters and Ben Wills" is provided in this record**
Soil data for biophysical models in Victoria, Australia : Current needs and future challenges
- Robinson, Nathan, Dahlhaus, Peter, MacEwan, Richard, Alexander, J. K.
- Authors: Robinson, Nathan , Dahlhaus, Peter , MacEwan, Richard , Alexander, J. K.
- Date: 2016
- Type: Text , Journal article
- Relation: Geoderma Regional Vol. 7, no. 3 (2016), p. 259-270
- Full Text: false
- Reviewed:
- Description: The use of biophysical models to support increased food production and environmental protection is on the rise. This paper reviews the demand for, and trends in, soil property data for various biophysical models being used in Victoria, Australia, over the 2009-2014 period. The study used surveys, workshops and interviews with public sector modellers to examine perceptions of the soil parameters that affect model sensitivity and error. Although the data requirements of models have remained similar over the 5 year period, the diversity of models used has decreased. There is evidence of increased application of models at point/site scale to support grains, dairy and livestock production industries in Victoria. Opportunities are identified to deliver finer scale soil data from digital soil mapping to better meet modelling requirements for agricultural industries in Victorian landscapes. © 2016 Elsevier B.V. All rights reserved.
Matching the model to the available data to predict wheat, barley, or canola yield : a review of recently published models and data
- Clark, Robert, Dahlhaus, Peter, Robinson, Nathan, Larkins, Jo-Ann, Morse-McNabb, Elizabeth
- Authors: Clark, Robert , Dahlhaus, Peter , Robinson, Nathan , Larkins, Jo-Ann , Morse-McNabb, Elizabeth
- Date: 2023
- Type: Text , Journal article , Review
- Relation: Agricultural Systems Vol. 211, no. (2023), p.
- Full Text:
- Reviewed:
- Description: CONTEXT: Continued increases in global population and rising living standards in many countries are driving a surge in demand for energy and protein-rich foods. Wheat, barley, and canola are important crops that are grown and traded globally. However, climate change, geopolitical tensions and competition from other crops threaten the ability to satisfy global demand. Accurate predictions of crop production and its spatial variation can play a significant role in their reliable and efficient production, marketing, and distribution. OBJECTIVE: This review examined recently published models and data used to predict wheat, barley, and canola yield to identify which factors produced the best yield predictions. METHODS: A literature search was conducted across the Scopus, EBSCOhost and Web of Science databases over seven years between 2015 and 2021. Data extracted from the papers identified by the literature search were investigated using graphical and quantitative analytical techniques to determine if the type of algorithm, input data, prediction timing, output scale or extent and climate variability both in isolation and in combination affected the model's predictive ability. RESULTS AND CONCLUSIONS: The literature search produced 11, 908 results which was reduced to 118 papers after applying the review criteria (peer reviewed papers focussed on models predicting yield at greater than plot scale across extensive areas using accessible data). China produced almost one third of all yield prediction models over the study period and 87% of models were used to predict wheat yield. Statistical models were the most common algorithm in most regions and in total. However, there was a surge in machine learning models after 2018. They were the most common model from 2019 to 2021, with one third developed in China. The review concluded that only the choice of modelling technique and the input data had a significant effect on model performance with the machine learning techniques Random Forest, Boosting algorithms and Deep Learning models as well as process-based Light Use Efficiency models that used a combination of remotely sensed and agrometeorological data performing best. SIGNIFICANCE: The review showed that matching the model to the available data could improve the ability to predict wheat, barley or canola yield. The use of quantitative statistical techniques in this review, should give modellers trying to predict wheat, barley or canola yield more confidence in matching their approach to the available data than previous reviews that relied on visual interpretation of data. © 2023 The Authors
- Authors: Clark, Robert , Dahlhaus, Peter , Robinson, Nathan , Larkins, Jo-Ann , Morse-McNabb, Elizabeth
- Date: 2023
- Type: Text , Journal article , Review
- Relation: Agricultural Systems Vol. 211, no. (2023), p.
- Full Text:
- Reviewed:
- Description: CONTEXT: Continued increases in global population and rising living standards in many countries are driving a surge in demand for energy and protein-rich foods. Wheat, barley, and canola are important crops that are grown and traded globally. However, climate change, geopolitical tensions and competition from other crops threaten the ability to satisfy global demand. Accurate predictions of crop production and its spatial variation can play a significant role in their reliable and efficient production, marketing, and distribution. OBJECTIVE: This review examined recently published models and data used to predict wheat, barley, and canola yield to identify which factors produced the best yield predictions. METHODS: A literature search was conducted across the Scopus, EBSCOhost and Web of Science databases over seven years between 2015 and 2021. Data extracted from the papers identified by the literature search were investigated using graphical and quantitative analytical techniques to determine if the type of algorithm, input data, prediction timing, output scale or extent and climate variability both in isolation and in combination affected the model's predictive ability. RESULTS AND CONCLUSIONS: The literature search produced 11, 908 results which was reduced to 118 papers after applying the review criteria (peer reviewed papers focussed on models predicting yield at greater than plot scale across extensive areas using accessible data). China produced almost one third of all yield prediction models over the study period and 87% of models were used to predict wheat yield. Statistical models were the most common algorithm in most regions and in total. However, there was a surge in machine learning models after 2018. They were the most common model from 2019 to 2021, with one third developed in China. The review concluded that only the choice of modelling technique and the input data had a significant effect on model performance with the machine learning techniques Random Forest, Boosting algorithms and Deep Learning models as well as process-based Light Use Efficiency models that used a combination of remotely sensed and agrometeorological data performing best. SIGNIFICANCE: The review showed that matching the model to the available data could improve the ability to predict wheat, barley or canola yield. The use of quantitative statistical techniques in this review, should give modellers trying to predict wheat, barley or canola yield more confidence in matching their approach to the available data than previous reviews that relied on visual interpretation of data. © 2023 The Authors
- «
- ‹
- 1
- ›
- »