Enabling Regenerative Agriculture Using Remote Sensing and Machine Learning

Abstract

The emergence of cloud computing, big data analytics, and machine learning has catalysed the use of remote sensing technologies to enable more timely management of sustainability indicators, given the uncertainty of future climate conditions. Here, we examine the potential of “regenerative agriculture”, as an adaptive grazing management strategy to minimise bare ground exposure while improving pasture productivity. High-intensity sheep grazing treatments were conducted in small fields (less than 1 ha) for short durations (typically less than 1 day). Paddocks were subsequently spelled to allow pasture biomass recovery (treatments comprising 3, 6, 9, 12, and 15 months), with each compared with controls characterised by lighter stocking rates for longer periods (2000 DSE/ha). Pastures were composed of wallaby grass (Austrodanthonia species), kangaroo grass (Themeda triandra), Phalaris (Phalaris aquatica), and cocksfoot (Dactylis glomerata), and were destructively sampled to estimate total standing dry matter (TSDM), standing green biomass, standing dry biomass and trampled biomass. We invoked a machine learning model forced with Sentinel-2 imagery to quantify TSDM, standing green and dry biomass. Faced with La Nina conditions, regenerative grazing did not significantly impact pasture productivity, with all treatments showing similar TSDM, green biomass and recovery. However, regenerative treatments significantly impacted litterfall and trampled material, with high-intensity grazing treatments trampling more biomass, increasing litter, enhancing surface organic matter and decomposition rates thereof. Pasture digestibility and sward uniformity were greatest for treatments with minimal spelling (3 months), whereas both standing senescent and trampled material were greater for the 15-month spelling treatment. TSDM prognostics from machine learning were lower than measured TSDM, although predictions from the machine learning approach closely matched observed spatiotemporal variability within and across treatments. The root mean square error between the measured and modelled TSDM was 903 kg DM/ha, which was less than the variability measured in the field. We conclude that regenerative grazing with short recovery periods (3–6 months) was more conducive to increasing pasture production under high rainfall conditions, and we speculate that – in this environment - high-intensity grazing with 3-month spelling is likely to improve soil organic carbon through increased litterfall and trampling. Our study paves the way for using machine learning with satellite imagery to quantify pasture biomass at small scales, enabling the management of pastures within small fields from afar.

Global Application of Regenerative Agriculture: A Review of Definitions and Assessment Approaches

“…Recent studies highlight the extensive use of machine learning in RA [28,29]. To explore its potential in bioeconomic modeling, a comprehensive literature review was conducted.…”

“…Geographic information systems (GIS) and remote sensing (RS) aid in crop monitoring, land use planning, yield estimation, soil mapping, fertility management, vegetation and biomass assessment [153]. For example, Ogungbuyi et al [28] used machine learning and satellite imagery for remote small-scale pasture management in Australia, focusing on RA to enhance pasture productivity and reduce bare ground exposure. Their study involved biomass sampling of various pasture types (i.e., wallaby grass, kangaroo grass, Phalaris, and cocksfoot) and employed machine learning with Sentinel-2 imagery to estimate biomass.…”

“…Evaluating RA requires considering farm economics, ecological services, and system maintenance, as environmental benefits alone are likely insufficient to motivate many farmers to transition [27]. Comprehensive modeling, integrating indicators, methodologies, bioeconomic models, and advanced analytics (Artificial intelligence (AI) and Machine learning (ML)) can establish an assessment framework for RA [28,29]. However, there is still a lack of research and reviews that thoroughly assess the biophysical and economic aspects.…”

“…Field-level models, such as Soil Navigator and the open soil index, consider various soil features but lack a comprehensive assessment of the environmental and socioeconomic implications of farm-level soil management practices [40,41]. The emergence of AI, big data analytics, and machine learning has catalyzed studies on the quantification of grassland biomass and regenerative grazing in many countries using remote sensing technologies [28,29]. Nevertheless, these studies frequently have limited geographical scope, primarily concentrate on agronomic aspects, and tend to overlook economic assessments, disregarding the intricate complexities inherent in the RA system.…”

Using Unmanned Aerial Vehicles and Multispectral Sensors to Model Forage Yield for Grasses of Semiarid Landscapes

“…There are reports that satellite imagery has been used to model forage biomass for Phalaris aquatica and Dactylis glomerata. In that study, they used satellite remote sensing and machine learning techniques to quantify the total standing dry matter (TSDM), standing green biomass, and standing dry biomass of these two species [44]. This research demonstrated the use of remote sensing technology, specifically satellite imagery, to model forage biomass.…”