Agriculture, a cornerstone of human civilization, faces rising challenges from climate change, resource limitations, and stagnating yields. Precise crop production forecasts are crucial for shaping trade policies, development strategies, and humanitarian initiatives. This study introduces a comprehensive machine learning framework designed to predict crop production. We leverage CMIP5 climate projections under a moderate carbon emission scenario to evaluate the future suitability of agricultural lands and incorporate climatic data, historical agricultural trends, and fertilizer usage to project yield changes. Our integrated approach forecasts significant regional variations in crop production across Southeast Asia by 2028, identifying potential cropland utilization. Specifically, the cropland area in Indonesia, Malaysia, Philippines, and Viet Nam is projected to decline by more than 10% if no action is taken, and there is potential to mitigate that loss. Moreover, rice production is projected to decline by 19% in Viet Nam and 7% in Thailand, while the Philippines may see a 5% increase compared to 2021 levels. Our findings underscore the critical impacts of climate change and human activities on agricultural productivity, offering essential insights for policy-making and fostering international cooperation.

BACKGROUND: Stress during pregnancy can lead to adverse maternal and infant health outcomes through epigenetic changes in the hypothalamic-pituitary-adrenal axis. Among farmers in low-income countries, one important stressor is food insecurity, which can be reduced using hermetic storage bags. This study aimed to determine, for the first time, whether a hermetic storage bag intervention during pregnancy positively affects maternal and infant DNA methylation of the hypothalamic-pituitary-adrenal axis-related genes FKBP5 and NR3C1. We further analyzed whether anthropometrics, stress, and mental health were associated with DNA methylation.
METHODS: This study was part of a larger matched-pair randomized controlled trial focusing on the impact of improved on-farm storage on food security, poverty, and net income of smallholder farming households. A total of N = 149 mothers were recruited by telephone and invited to attend a study appointment at health facilities in Kakamega County, Western Kenya, with their infants in April or May 2021. During the appointment, anthropometric measurements were taken, questionnaires on stress and mental health were administered, and saliva samples were collected. Logistic and multiple linear regression were used to examine the effect of the intervention and related measures on DNA methylation.
RESULTS: Mothers in the intervention group showed higher mean NR3C1 methylation levels than those in the control group, corrected for multiple testing. Maternal postpartum body mass index was positively associated with infant NR3C1 CpG3 DNA methylation. The more stressful life events a mother had experienced in the previous 12 months (including during pregnancy), the lower her FKBP5 CpG3 methylation levels.
CONCLUSIONS: Food insecurity and stressful life events during pregnancy seem to exert significant effects on maternal DNA methylation. While these stressors did not appear to impact infant DNA methylation in the present study, maternal postpartum body mass index was significantly related to infant methylation. These findings suggest that while infants may be protected from excessive maternal glucocorticoids by placental barrier activity, maternal metabolic status is still reflected in their epigenetic make-up. Trial registration This study was part of a larger matched-pair randomized controlled trial on the impact of improved on-farm crop storage on welfare, nutrition, and human health. Registration can be found in the American Economic Association (AEA) RCT Registry, RCT ID: AEARCTR-0005845.

The intensive global use of pesticides presents an escalating threat to human health, ecosystems, and water quality. To develop national and local environmental management strategies for mitigating pollution caused by pesticides, it is essential to understand the quantities, timing, and location of their application. This study aims to estimate the spatial distribution of pesticide use in an agricultural region of La Plata River basin in Uruguay. Estimates of pesticide use were made by surveying doses applied to each crop. This information was spatialized through identifying agricultural rotations using remote sensing techniques. The study identified the 60 major agricultural rotations in the region and mapped the use and application amount of the nine most significant active ingredients (glyphosate, 2,4-dichlorophenoxyacetic acid, flumioxazin, S-metolachlor, clethodim, flumetsulam, triflumuron, chlorantraniliprole, and fipronil). The results reveal that glyphosate is the most extensively used pesticide (53.5% of the area) and highest amount of use (> 1.44 kg/ha). Moreover, in 19% of the area, at least seven active ingredients are applied in crop rotations. This study marks the initial step in identifying rotations and estimating pesticide applications with high spatial resolution at a regional scale in agricultural regions of La Plata River basin. The results improve the understanding of pesticide spatial distribution based on data obtained from agronomists, technicians, and producers and provide a replicable methodological approach for other geographic and productive contexts. Generating baseline information is key to environmental management and decision making, towards the design of more robust monitoring systems and human exposure assessment.

Advancements in imaging, computer vision, and automation have revolutionized various fields, including field-based high-throughput plant phenotyping (FHTPP). This integration allows for the rapid and accurate measurement of plant traits. Deep Convolutional Neural Networks (DCNNs) have emerged as a powerful tool in FHTPP, particularly in crop segmentation-identifying crops from the background-crucial for trait analysis. However, the effectiveness of DCNNs often hinges on the availability of large, labeled datasets, which poses a challenge due to the high cost of labeling. In this study, a deep learning with bagging approach is introduced to enhance crop segmentation using high-resolution RGB images, tested on the NU-Spidercam dataset from maize plots. The proposed method outperforms traditional machine learning and deep learning models in prediction accuracy and speed. Remarkably, it achieves up to 40% higher Intersection-over-Union (IoU) than the threshold method and 11% over conventional machine learning, with significantly faster prediction times and manageable training duration. Crucially, it demonstrates that even small labeled datasets can yield high accuracy in semantic segmentation. This approach not only proves effective for FHTPP but also suggests potential for broader application in remote sensing, offering a scalable solution to semantic segmentation challenges. This paper is accompanied by publicly available source code.

Border crops can increase beneficial insect biodiversity within agricultural fields by supplementing insects with food and nesting resources. However, the effectiveness of border crops relies on insect movement between adjacent habitats and some insects might consider habitat boundaries as barriers. Therefore, understanding insect movement between habitats is needed to determine the effectiveness of border crops for ecosystem services such as pest control within agricultural habitats. Our objective was to compare ground beetle (Coleoptera: Carabidae) movement across soybean plots that were bordered by corn and grassland habitat to determine whether habitat boundaries were considered barriers of movement to predatory beetles. Using a grid of pitfall traps within these habitats, we conducted a mark, release, and recapture experiment to track and evaluate ground beetle movement patterns. We found that ground beetles stayed in the habitat of their release and that movement between habitats, despite the type of bordering habitat or type of edge, was uncommon. We also found that long-distance movement was rare as most beetles moved less than 5 m (regardless of release or recaptured habitat) and movement was perpendicular to habitat edges. These results suggest that any edge habitat, including agricultural-agricultural boundaries and natural-agricultural boundaries, are likely barriers to ground beetle movement. Therefore, in order for border crops to be effective in pest management by ground beetles, making habitat edges more permeable, especially using techniques such as edge softening, could promote cross-habitat movement and ultimately contribute to natural pest control in agricultural systems.

Onion is a vital vegetable crop in Ethiopia, with significant economic and health benefits. However, its production trend is not consistent, with periods of increase and decrease; and its productivity in the country falls far below its potential. As a result, farmers are not yet fully benefited from onion production. Thus, this study was initiated to identify the factors influencing onion production in the Raya Kobo District of Amhara Regional State of Ethiopia. Data was collected from 189 onion-producing farmers through household surveys, and both descriptive and econometric techniques were used for analysis. The study found significant variation in onion production among farmers, with lower levels compared to national and international averages. Factors such as gender, education level, experience, labor force, land size, access to extension services, irrigation water, land plough frequency, and fertilizer availability positively impact onion production. However, excessive fertilizer use was found to have a negative effect. The study also identified challenges faced by farmers, including input shortages, high costs, diseases, labor issues, soil infertility, and storage knowledge gaps. The study recommends policymakers and stakeholders to utilize these findings to develop effective policies and interventions that can enhance onion production, benefiting farmers and improving the overall onion production.

Suitable combinations of observed datasets for estimating crop model parameters can reduce the computational cost while ensuring accuracy. This study aims to explore the quantitative influence of different combinations of the observed phenological stages on estimation of cultivar-specific parameters (CPSs). We used the CROPGRO-Soybean phenological model (CSPM) as a case study in combination with the Generalized Likelihood Uncertainty Estimation (GLUE) method. Different combinations of four observed phenological stages, including initial flowering, initial pod, initial grain, and initial maturity stages for five soybean cultivars from Exp. 1 and Exp. 3 described in Table 2 are respectively used to calibrate the CSPs. The CSPM, driven by the optimized CSPs, is then evaluated against two independent phenological datasets from Exp. 2 and Exp. 4 described in Table 2. Root means square error (RMSE) (mean absolute error (MAE), coefficient of determination (R2), and Nash Sutcliffe model efficiency (NSE)) are 15.50 (14.63, 0.96, 0.42), 4.76 (3.92, 0.97, 0.95), 4.69 (3.72, 0.98, 0.95), 3.91 (3.40, 0.99, 0.96) and 12.54 (11.67, 0.95, 0.60), 5.07 (4.61, 0.98, 0.93), 4.97 (4.28, 0.97, 0.94), 4.58 (4.02, 0.98, 0.95) for using one, two, three, and four observed phenological stages in the CSPs estimation. The evaluation results suggest that RMSE and MAE decrease, and R2 and NSE increase with the increase in the number of observed phenological stages used for parameter calibration. However, there is no significant reduction in the RMSEs (MAEs, NSEs) using two, three, and four observed stages. Relatively reliable optimized CSPs for CSMP are obtained by using at least two observed phenological stages balancing calibration effect and computational cost. These findings provide new insight into parameter estimation of crop models.

Decoupling of crop-livestock systems increases the risks of pollution, waste of nutrient resources, and biodiversity loss. Crop-livestock integration (CLI) is an effective solution to these problems, and motivating farmers to adopt CLI is the key. Many countries have implemented environmental regulations (ER) aiming to influence farmers\' CLI adoption decisions. Based on a field study of 316 hog farmers from Shaanxi Province of China, this paper applies the triple-hurdle model to empirically examine the impacts of economic expectations (EE) and ER on CLI adoption decisions. It also verifies the income effect of CLI. The results are as follows: 90.5% of farmers are willing to adopt CLI, but the adoption rate is only 40.8% and the average integration degree is only 0.236; CLI not been widely popularized. EE and ER promote farmers\' CLI adoption significantly, while the impact of interaction between EE and ER on CLI adoption differs. IER weakens the positive impact of EE on farmers\' CLI integration degree, which has a \"crowding out effect.\" GER negatively moderates the impact of EE on farmers\' adoption willingness of CLI. CER strengthens the positive effect of EE on farmers\' adoption behavior and CLI integration degree. CLI increases the farmers\' income. These results contribute to our understanding of the mechanisms of CLI adoption decisions and sustainable policy optimization for green agricultural development.

Carbon:nitrogen:phosphorus (C:N:P) stoichiometry plays a vital role in regulating P transformation in agriculture ecosystems. However, the impact of balanced C:N:P stoichiometry in paddy soil, particularly regarding relative soil P transformation, remains unknown. This study explores the response of C:N:P stoichiometry to manure substitution and its regulatory role in soil P transformation, along with the associated release risk to the environment. Based on a 5-year field study, our findings reveal that replacing 30 % of chemical P fertilizer with pig manure (equal total NPK amounts with chemical P fertilizer treatment, named CFM) increased soil total C without altering soil total P, resulting in an elevated soil C:P ratio, despite the homeostasis of crop stoichiometry. This increase promoted microbial diversity and the accumulation of organic P in the soil. The Proteobacteria and Actinobacteria produced lower C:PEEA metabolism together, and enhanced in vivo turnover of P. Additionally, by integrating high-resolution dialysis (HR-Peeper), diffusive gradients in thin films (DGT), DGT-induced fluxes in the soil (DIFS), and sediment P release risk index (SPRRI) models, we observed that, in addition to organic P, CFM simultaneously increased soil Al-P, thereby weakening the diffusion and resupply capacity of P from soil solids to the solution. Consequently, this decrease in P release risk to the environment was demonstrated. Overall, this study establishes a connection between crop-soil-enzyme C:N:P stoichiometry, soil microorganisms, and soil P biogeochemical processes. The study further evaluates the P release risk to the environment, providing a novel perspective on both the direct and indirect effects of manure substitution on soil P cycling.

Landraces are important genetic resources that have a significant role in maintaining the long-term sustainability of traditional agro-ecosystems, food, nutrition, and livelihood security. In an effort to document landraces in the on-farm conservation context, Central Western Ghat region in India was surveyed. A total of 671 landraces belonging to 60 crops were recorded from 24 sites. The custodian farmers were found to conserve a variety of crops including vegetables, cereals and pulses, perennial fruits, spices, tuber and plantation crops. The survey indicated a difference in the prevalence of landraces across the sites. A significant difference with respect to the Shannon-diversity index, Gini-Simpson index, evenness, species richness, and abundance was observed among the different survey sites. Computation of a prevalence index indicated the need for immediate intervention in the form of collecting and ex situ conservation of landraces of some crops as a back-up to on-farm conservation. The study also identified the critical determinants of on-farm conservation, including (i) suitability to regional conditions, (ii) relevance in regional cuisine and local medicinal practices, (iii) cultural and traditional significance, and (iv) economic advantage. The information documented in this study is expected to promote the collection and conservation of landraces ex situ. The National Genebank housed at ICAR-NBPGR, New Delhi conserves around 550 accessions of landraces collected from the Central Western Ghats region surveyed in this report. Information collected from custodian farmers on specific uses will be helpful to enhance the utilization of these accessions.