CATENA, Journal Year: 2024, Volume and Issue: 247, P. 108550 - 108550
Published: Nov. 15, 2024
Language: Английский
CATENA, Journal Year: 2024, Volume and Issue: 247, P. 108550 - 108550
Published: Nov. 15, 2024
Language: Английский
European Journal of Soil Science, Journal Year: 2025, Volume and Issue: 76(1)
Published: Jan. 1, 2025
ABSTRACT Over the past 60 years, efforts to enhance agricultural productivity have mainly focussed on optimising strategies such as use of inorganic fertilisers, advancements in microbiology and improved water management practices. Here, we emphasise critical role pedology a foundation soil long‐term sustainability. We will demonstrate how overlooking intrinsic properties soils can result detrimental effects overall Communication between academia, extension experts, consultants farmers often results an overemphasis surface layer, for example, 20 40 cm, neglecting functions that occur at depth. Soil health regenerative agriculture must be coupled with understanding dynamic system. find pedological knowledge digital mapping technologies are underused achieving sustainable agriculture. By bridging gap emerging technologies, provide land users tools needed make informed decisions, ensuring their practices not only increase production but also preserve future generations.
Language: Английский
Citations
1CATENA, Journal Year: 2025, Volume and Issue: 256, P. 109145 - 109145
Published: May 11, 2025
Language: Английский
Citations
0Frontiers in Environmental Science, Journal Year: 2025, Volume and Issue: 13
Published: May 16, 2025
Accurate and cost-effective mapping of soil organic carbon (SOC) is critical for understanding dynamics informing sustainable land management. Although deep learning-based methods have demonstrated strong potential in digital mapping, they typically require large amounts data. However, the availability site-level SOC observations often limited, which poses a challenge model performance. To address this, we propose novel transfer learning approach based on Convolutional Neural Network (CNN) that does not rely exogenous Specifically, when predicting given layer, first pre-trained data from all layers then fine-tuned using target layer. This design enables more efficient use limited site Experimental results show proposed consistently outperforms other machine models, including Random Forest (RF), standard CNN, Multi-Task CNN (MTCNN) models. The achieves coefficient determination (R 2 ) 0.374 root mean square error (RMSE) 2.937%, indicating superior These findings highlight effectiveness under data-scarce conditions underscore its as robust tool accurate estimation.
Language: Английский
Citations
0Soil Science Society of America Journal, Journal Year: 2024, Volume and Issue: 88(6), P. 2211 - 2226
Published: Sept. 14, 2024
Abstract Silvopastoral system (SPS) is a multifunctional agroforestry practice. This study evaluate soil properties and root biomass under SPS in Pernambuco, Brazil. The experiment was established 2011. treatments were (1) monoculture signalgrass (MS) [ Urochloa decumbens (Stapf.) R. D. Webster], (2) intercropped pasture of with legume Gliricidia (SG) sepium (Jacq.) Steud.], (3) sabiá (SS) ( Mimosa caesalpiniifolia Benth). Treatments allocated randomized complete block design three replications. Samples collected at 0‐ to 10‐, 10‐ 20‐, 20‐ 40‐, 40‐ 60‐, 60‐ 80‐, 80‐ 100‐, 100‐ 120‐cm depths. Soil samples also taken from the native forest (NF) considered as reference same Experimental Station. Legume (SG SS) presented greater per unit area compared MS 80‐cm depth p < 0.05); however, had hectare top layers. average values weighted mean diameter aggregates 3.20, 3.19, 3.07, 3.27 mm MS, SG, SS, NF, respectively, increased cation exchange capacity deeper layers, indicating biological activity depth. Grasslands store 235 Mg C ha−1 71% that found layers (20–120 cm). arboreal legumes has potential improve deep storage resilience livestock systems tropical regions.
Language: Английский
Citations
3CATENA, Journal Year: 2024, Volume and Issue: 247, P. 108550 - 108550
Published: Nov. 15, 2024
Language: Английский
Citations
0