Search

Integrated crop–livestock systems (ICLS) are among the main viable strategies for sustainable agricultural production. Mapping these systems is crucial for monitoring land use changes in Brazil, playing a significant role in promoting sustainable agricultural production. Due to the highly dynamic nature of ICLS management, mapping them is a challenging task. The main objective of this research was to develop a method for mapping ICLS using deep learning algorithms applied on Satellite Image Time Series (SITS) data cubes, which consist of Sentinel-2 (S2) and PlanetScope (PS) satellite images, as well as data fused (DF) from both sensors. This study focused on two Brazilian states with varying landscapes and field sizes. Targeting ICLS, field data were combined with S2 and PS data to build land use and land cover classification models for three sequential agricultural years (2018/2019, 2019/2020, and 2020/2021). We tested three experimental settings to assess the classification performance using S2, PS, and DF data cubes. The test classification algorithms included Random Forest (RF), Temporal Convolutional Neural Network (TempCNN), Residual Network (ResNet), and a Lightweight Temporal Attention Encoder (L-TAE), with the latter incorporating an attention-based model, fusing S2 and PS within the temporal encoders. Experimental results did not show statistically significant differences between the three data sources for both study areas. Nevertheless, the TempCNN outperformed the other classifiers with an overall accuracy above 90% and an F1-Score of 86.6% for the ICLS class. By selecting the best models, we generated annual ICLS maps, including their surrounding landscapes. This study demonstrated the potential of deep learning algorithms and SITS to successfully map dynamic agricultural systems. [ABSTRACT FROM AUTHOR]

Regenerative agricultural practices are a suitable path to feed the global population. Integrated Crop–livestock systems (ICLSs) are key approaches once the area provides animal and crop production resources. In Brazil, the expectation is to increase the area of ICLS fields by 5 million hectares in the next five years. However, few methods have been tested regarding spatial and temporal scales to map and monitor ICLS fields, and none of these methods use SAR data. Therefore, in this work, we explored the potential of three machine and deep learning algorithms (random forest, long short-term memory, and transformer) to perform early-season (with three-time windows) mapping of ICLS fields. To explore the scalability of the proposed methods, we tested them in two regions with different latitudes, cloud cover rates, field sizes, landscapes, and crop types. Finally, the potential of SAR (Sentinel-1) and optical (Sentinel-2) data was tested. As a result, we found that all proposed algorithms and sensors could correctly map both study sites. For Study Site 1(SS1), we obtained an overall accuracy of 98% using the random forest classifier. For Study Site 2, we obtained an overall accuracy of 99% using the long short-term memory net and the random forest. Further, the early-season experiments were successful for both study sites (with an accuracy higher than 90% for all time windows), and no significant difference in accuracy was found among them. Thus, this study found that it is possible to map ICLSs in the early-season and in different latitudes by using diverse algorithms and sensors. [ABSTRACT FROM AUTHOR]

Tropical soils are prone to rapid degradation if not managed well, and agroforestry systems have the potential to restore degraded soils and support agricultural production together with other ecosystem services. In Brazil, an increasing number of pioneering farmers are establishing agroforestry systems on previously cleared farmland. However, while there are a wide range of agroforestry systems, this diversity has hardly been quantified, and it is not clear how these systems differ in their capacity for nutrient cycling to reverse soil degradation. The objectives of the study were to assess innovative agroforestry systems in terms of taxonomic and functional diversity, spatial structure and management, and to assess how these systems differ in terms of structural complexity and their potential for nutrient cycling. We assessed a LiDAR-derived stand structural complexity index (SSCI), interrow spacing, stem density, tree species richness and diversity, community weighted means (CWM) of foliar nitrogen and wood density, livestock density, pruning and mowing regimes in 30 agroforestry systems in the state of São Paulo, Brazil. We used N, P, K, Ca and Mg stocks in litter as a proxy for nutrient cycling. The agroforestry systems could be broadly categorized into silvopastures, multistrata and successional agroforestry systems. These types spanned a gradient of structural complexity, and this complexity was positively associated with tree species richness and planting density. Litter nutrient stocks were positively associated with pruning and mulching, and negatively associated with CWM of wood density, indicating the importance of pioneer trees. Overall, our results suggest that densely planted, pruned agroforestry systems that contain high species richness, including pioneer trees, contain relatively high amounts of N, P, K, Ca and Mg in their litter. These findings provide insight in the key characteristics of agroforestry systems to support nutrient cycling, and can inform the design of agroforestry systems for the regeneration of degraded agricultural land. • There is a wide diversity of agroforestry systems established in Brazil. • Terrestrial LiDAR-derived index showed a structural complexity gradient among agroforests. • Structural complexity is associated with tree species richness and planting density. • Pruning & mulching of pioneer tree species can enhance nutrient cycling of N, P, K, Ca and Mg. [ABSTRACT FROM AUTHOR]