首页|Studies from ARC Centre of Excellence for Climate Extremes Provide New Data on M achine Learning (An ensemble estimate of Australian soil organic carbon using ma chine learning and processbased modelling)
Studies from ARC Centre of Excellence for Climate Extremes Provide New Data on M achine Learning (An ensemble estimate of Australian soil organic carbon using ma chine learning and processbased modelling)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – New study results on artificial intell igence have been published. According to news reporting from Sydney, Australia, by NewsRx journalists, research stated, “Spatially explicit prediction of soil o rganic carbon (SOC) serves as a crucial foundation for effective land management strategies aimed at mitigating soil degradation and assessing carbon sequestrat ion potential.” The news editors obtained a quote from the research from ARC Centre of Excellenc e for Climate Extremes: “Here, using more than 1000 in situ observations, we tra ined two machine learning models (a random forest model and a * * k* * -means co upled with multiple linear regression model) and one process-based model (the ve rtically resolved MIcrobial-MIneral Carbon Stabilization, MIMICS, model) to pred ict the SOC stocks of the top 30 cm of soil in Australia. Parameters of MIMICS w ere optimised for different site groupings using two distinct approaches: plant functional types (MIMICS-PFT) and the most influential environmental factors (MI MICS-ENV). All models showed good performance with respect to SOC predictions, w ith an * * R* * 2 value greater than 0.8 during out-of-sample validation, with random forest bein g the most accurate; moreover, it was found that SOC in forests is more predicta ble than that in non-forest soils excluding croplands. The performance of contin ental-scale SOC predictions by MIMICS-ENV is better than that by MIMICS-PFT espe cially in non-forest soils. Digital maps of terrestrial SOC stocks generated usi ng all of the models showed a similar spatial distribution, with higher values i n south-eastern and south-western Australia, but the magnitude of the estimated SOC stocks varied. The mean ensemble estimate of SOC stocks was 30.3 t ha ~(-1), with * * k* * -means coupled with multiple linear regression generating the hi ghest estimate (mean SOC stocks of 38.15 t ha ~(-1)) and MIMICS-PFT generating the lowest estimate (mean SOC stocks of 24.29 t ha ~(-1)).”
ARC Centre of Excellence for Climate Ext remesSydneyAustraliaAustralia and New ZealandCyborgsEmerging Technolog iesMachine Learning
NETL
NSTL
