The increase in frequency and severity of extreme weather events poses challenges for the agricultural sector in developing economies and for food security globally. In this article, we demonstrate how machine learning can be used to mine satellite data and identify pixel-level optimal weather indices that can be used to inform the design of risk transfers and the quantification of the benefits of resilient production technology adoption. We implement the model to study maize production in Mozambique, and show how the approach can be used to produce countrywide risk profiles resulting from the aggregation of local, heterogeneous exposures to rainfall precipitation and excess temperature. We then develop a framework to quantify the economic gains from technology adoption by using insurance costs as the relevant metric, where insurance is broadly understood as the transfer of weather-driven crop losses to a dedicated facility. We consider the case of irrigation in detail, estimating a reduction in insurance costs of at least 30%, which is robust to different configurations of the model. The approach offers a robust framework to understand the costs versus benefits of investment in irrigation infrastructure, but could clearly be used to explore in detail the benefits of more advanced input packages, allowing, for example, for different crop varieties, sowing dates, or fertilizers.

Xylitol production from corncob hemicellulose is a popular process in China. Microbial conversion of xylose to xylitol, as a biological process with many advantages, has drawn increasing attention. As a by-product from the manufacturing of xylitol, corncob cellulosic residues are produced in very large amounts and represent an environmental problem. As a result, considering the large amount of xylitol production in China, the conversion of corncob cellulosic residues has become a widespread issue having to be tackled. After the hemicellulose in corncob has been hydrolyzed for xylitol production, the corncob cellulosic residue is porous and can easily be hydrolyzed by cellulases into glucose and further converted to ethanol, another high-added-value chemical. Based on the latest technology advancements in xylitol, cellulase, and ethanol production, the integrated production of ethanol from corncob cellulosic residues appears as a promising way to improve the profit of the whole xylitol production process.

The overall, end-to-end methodological construct is illustrated in Fig. 1. It relies on machine 37 learning involving weather indices that characterize the vulnerability of crops to weather 38 variability in different technological scenarios (Fig 1a). We here used a stochastic "weather-within-climate" downscaling approach that quantifies the 43 interaction of low-and high-frequency climate variability (Fig. 1b) The results demonstrate that important variations in province-level risk profiles depend on the 144 regional features of weather and climate variability. costs of damage. 188We propose a "three-pillar"-based approach for rural development and food security risk

In this paper we introduce the Temporo-Spatial Vision Transformer (TSViT), a fully-attentional model for general Satellite Image Time Series (SITS) processing based on the Vision Transformer (ViT). TSViT splits a SITS record into non-overlapping patches in space and time which are tokenized and subsequently processed by a factorized temporo-spatial encoder. We argue, that in contrast to natural images, a temporal-then-spatial factorization is more intuitive for SITS processing and present experimental evidence for this claim. Additionally, we enhance the model's discriminative power by introducing two novel mechanisms for acquisition-time-specific temporal positional encodings and multiple learnable class tokens. The effect of all novel design choices is evaluated through an extensive ablation study. Our proposed architecture achieves state-of-the-art performance, surpassing previous approaches by a significant margin in three publicly available SITS semantic segmentation and classification datasets. All model, training and evaluation codes are made publicly available in https://github.com/michaeltrs/DeepSatModels.

The Bovine Respiratory Disease Coordinated Agricultural Project (BRD CAP) is a 5-year project funded by the United States Department of Agriculture (USDA), with an overriding objective to use the tools of modern genomics to identify cattle that are less susceptible to BRD. To do this, two large genome wide association studies (GWAS) were conducted using a case:control design on preweaned Holstein dairy heifers and beef feedlot cattle. A health scoring system was used to identify BRD cases and controls. Heritability estimates for BRD susceptibility ranged from 19 to 21% in dairy calves to 29.2% in beef cattle when using numerical scores as a semi-quantitative definition of BRD. A GWAS analysis conducted on the dairy calf data showed that single nucleotide polymorphism (SNP) effects explained 20% of the variation in BRD incidence and 17-20% of the variation in clinical signs. These results represent a preliminary analysis of ongoing work to identify loci associated with BRD. Future work includes validation of the chromosomal regions and SNPs that have been identified as important for BRD susceptibility, fine mapping of chromosomes to identify causal SNPs, and integration of predictive markers for BRD susceptibility into genetic tests and national cattle genetic evaluations.