Using remote sensing, process-based crop models, and machine learning to evaluate crop rotations across 20 million hectares in Western Australia

Lawes, Roger; Mata, G.; Richetti, Jonathan; Fletcher, Andrew; Herrmann, Chris

doi:10.1007/s13593-022-00851-y

Cited by 7 publications

(3 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Still, these methods can provide trends and assess regional practice changes much quicker than surveys. For example, detecting sowing practices changes with the introduction of new crop cultivars, i.e., a cultivar that could be sown deeper and, hence, earlier in dry lands to capture early rains [62] or crop models that could be informed to evaluate large regions [63]. The main goal of these algorithms is to quickly produce a sowing and harvest date map over a large area.…”

Section: Discussionmentioning

confidence: 99%

Estimating Crop Sowing and Harvesting Dates Using Satellite Vegetation Index: A Comparative Analysis

Rodigheri,

Sanches,

Richetti

et al. 2023

Remote Sensing

Self Cite

View full text Add to dashboard Cite

In the last decades, several methodologies for estimating crop phenology based on remote sensing data have been developed and used to create different algorithms. Although many studies have been conducted to evaluate the different methodologies, a comprehensive understanding of the potential of the different current algorithms to detect changes in the growing season is still lacking, especially in large regions and with more than one crop per season. Therefore, this work aimed to evaluate different phenological metrics extraction methodologies. Using data from over 1500 fields distributed across Brazil’s central area, six algorithms, including CropPhenology, Digital Earth Australia tools package (DEA), greenbrown, phenex, phenofit, and TIMESAT, to extract soybean crop phenology were applied. To understand how robust the algorithms are to different input sources, the NDVI and EVI2 time series derived from MODIS products (MOD13Q1 and MOD09Q1) and from Sentinel-2 satellites were used to estimate the sowing date (SD) and harvest date (HD) in each field. The algorithms produced significantly different phenological date estimates, with Spearman’s R ranging between 0.26 and 0.82 when comparing sowing and harvesting dates. The best estimates were obtained using TIMESAT and phenex for SD and HD, respectively, with R greater than 0.7 and RMSE of 16–17 days. The DEA tools and greenbrown packages showed higher sensitivity when using different data sources. Double cropping is an added challenge, with no method adequately identifying it.

show abstract

Section: Discussionmentioning

confidence: 99%

Estimating Crop Sowing and Harvesting Dates Using Satellite Vegetation Index: A Comparative Analysis

Rodigheri,

Sanches,

Richetti

et al. 2023

Remote Sensing

Self Cite

View full text Add to dashboard Cite

show abstract

“…Over the same period, the area cropped has increased by more than 60% (Perret 2015). Together with lower whole-farm stocking rates (Bell and Moore 2012), this has resulted in many pastures becoming a fallow dominated by weedy volunteer species with poor nutritional value and suboptimal break-crop benefits for cereal production (Lawes et al 2022). Modelling, focused on the MFZ of Western Australia, indicates that fallows are unlikely to increase overall grain productivity, with the exception of very low rainfall, weedy or diseased paddocks (Chen et al 2023).…”

Section: Livestock and Pastures In The Mixed Farming Zonementioning

confidence: 99%

Livestock preference and feeding value as key determinants for forage improvement – why not ask the consumers?

Norman

Masters

2023

Anim. Prod. Sci.

View full text Add to dashboard Cite

This review presents a new model for a multidisciplinary approach to development of modern forage cultivars to enable high-value meat and wool production in the mixed farming zones of Australia. Many pasture improvement activities focus on biomass production, filling novel agro-ecological niches, fixing nitrogen and phenotypic markers. Key traits that drive profitability of livestock, such as feeding value (FV), and nutritive value (NV), are rarely considered in a timely manner. Farmers are often not seriously engaged until late in the development pipeline. Of the nearly 10 000 publications that reference forage improvement or breeding and Australia, less than 5% also reference ruminant production factors such as FV, metabolisable energy, digestibility, methane or toxicity in the abstract, title or keywords. We make the case that the late engagement of livestock science and farmers results in early discarding of potentially valuable genetic material. This in turn may contribute to market and nutritional limitations that contribute to the high failure rate of new pasture cultivars. Four case studies demonstrated the within and among species variation in FV and NV. The first showed the variability in dry matter digestibility and crude protein of 20 species of herbaceous perennials at different stages of maturity. A second study with annual legumes, grasses and brassicas indicated highly significant differences in the rate of decline of NV over time and across species. The third case study focused on commercial and experimental accessions of lucerne and demonstrated highly significant differences among accessions in NV, with a doubling of livestock growth expected with the lowest and highest NV accessions. These case studies demonstrated the potential risks associated with evaluation of FV and NV after most of the germplasm has been excluded. The final case study described a different model that was used in the identification and commercialisation of a woody perennial species. This process incorporated a multidisciplinary team, farmers and livestock-relevant characteristics from the start. In 9 years, Anameka™ oldman saltbush was selected for higher palatability, 20% higher organic-matter digestibility and eight times more biomass than the average of the original genetic material.

show abstract

“…This would allow previously calibrated cultivars to be assessed and an understanding of how the model is expected to perform if extrapolated further. Finally, we combined APSIM Next Gen outputs and machine learning to provide insights into crop rotations across every paddock across 20 million hectares in Western Australia, where we show that the benefits of break-crops and pastures to farmers are less than the 400 to 600 kg/ha benefit commonly reported from field experiments (Lawes et al 2022).…”

mentioning

confidence: 99%

Building trust in continental-scale modelling in agriculture

2023

MODSIM2023, 25th International Congress on Modelling and Simulation.

View full text Add to dashboard Cite

All models are wrong, but some are useful. This famous sentence summarises modelling in all areas; however, determining model usefulness is challenging, particularly in complex systems such as agriculture. Building trust in models means providing evidence that their uncertainties and errors are acceptable for the decision-making process. Here we explore two ways to understand model usefulness in agriculture; a data-driven one and a mechanistic one. Lastly, we provide an example of combing data-driven and mechanist models to provide further insights into the agricultural landscape.Data-driven methods such as modern machine learning algorithms relying on techniques such as crossvalidation to reliably determine the model's usefulness (i.e. accuracy assessment). Cereal yields were forecasted with Deep Learning (DL) to show the implications of different architectures and provide some crossvalidation recommendations for the agricultural context (Richetti et al. 2023). It is shown that DL performance can vary with architecture and that the optimal choice is task-dependent. Practical aspects for applying DL models for agricultural datasets are emphasised, such as dataset size (26 representative samples in each field sufficed) and cross-validation (indispensable on small datasets). However, mechanistic models such as crop models (i.e. APSIM) are usually not assessed similarly. Thus, a different approach is often used to build trust and determine their usefulness. To determine how a crop model could be assessed on a continental scale, the APSIM Next Gen was combined with gridded soil and weather data and run across 14,796 national variety trials from 2005 to 2022 across the Australian continent with minimal management information (sowing date and cultivar). This would allow previously calibrated cultivars to be assessed and an understanding of how the model is expected to perform if extrapolated further. Finally, we combined APSIM Next Gen outputs and machine learning to provide insights into crop rotations across every paddock across 20 million hectares in Western Australia, where we show that the benefits of break-crops and pastures to farmers are less than the 400 to 600 kg/ha benefit commonly reported from field experiments (Lawes et al. 2022).Understanding the uncertainties of models is crucial for successfully deploying them. When modelling agriculture at a continental scale, the uncertainties are accentuated, and error sources are broadened. Nonetheless, by carefully crafting the accuracy assessments that reflect the reality in which the models are applied, the models can be useful.

show abstract

Using remote sensing, process-based crop models, and machine learning to evaluate crop rotations across 20 million hectares in Western Australia

Cited by 7 publications

References 44 publications

Estimating Crop Sowing and Harvesting Dates Using Satellite Vegetation Index: A Comparative Analysis

Estimating Crop Sowing and Harvesting Dates Using Satellite Vegetation Index: A Comparative Analysis

Livestock preference and feeding value as key determinants for forage improvement – why not ask the consumers?

Building trust in continental-scale modelling in agriculture

Contact Info

Product

Resources

About