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.

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.

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.

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.

Pesticides are critical for protecting agricultural crops, but the off-site transport of these materials via spray drift and runoff poses risks to surface waters and aquatic life. California\'s Central Coast region is a major agricultural hub in the United States characterized by year-round production and intensive use of pesticides and other chemical inputs. As a result, the quality of many waterbodies in the region has been degraded. A recent regulatory program enacted by the Central Coast Regional Water Quality Control Board set new pesticide limits for waterways and imposed enhanced enforcement mechanisms to help ensure that water quality targets are met by specific dates. This regulatory program, however, does not mandate specific changes to pest management programs. In this study, we evaluate the economic, environmental, and pest management impacts of adopting two alternative pest management programs with reduced risks to surface water: 1) replacing currently used insecticide active ingredients (AIs) that pose the greatest risk to surface water with lower-risk alternatives and 2) converting conventional arthropod pest management programs to organic ones. We utilize pesticide use and toxicity data from California\'s Department of Pesticide Regulation to develop our baseline and two alternative scenarios. We focus on three crop groups (cole crops, lettuce and strawberry) due to their economic importance to the Central Coast and use of high-risk AIs. For Scenario 1, we estimate that implementing the alternative program in the years 2017-2019 would have reduced annual net returns on average by $90.26 - $190.54/ha, depending on the crop. Increased material costs accounted for the greatest share of this effect (71.9%-95.6%). In contrast, Scenario 2 would have reduced annual net returns on average by $5,628.12 - $18,708.28/ha during the study period, with yield loss accounting for the greatest share (92.8-97.9%). Both alternative programs would have reduced the associated toxic units by at least 98.1% compared to the baseline scenario. Our analysis provides important guidance for policymakers and agricultural producers looking to achieve environmental protection goals while minimizing economic impacts.

UNASSIGNED: Greenhouse vertical farming under natural sunlight is an alternative farming technique that grows crops in a stacking column and extends in a vertical direction. Sunlight availability is one of the crucial factors for crop development in vertical farming. Therefore, this investigation aimed to examine the effect of sunlight availability on lettuce growth and yields at different levels of vertical shelves.
UNASSIGNED: Six shelves were constructed with three levels: upper, middle and lower levels. Lettuces (Lactuca sativa L.) as \'Baby Cos\' and \'Green Oak\' at 14 days after sowing were planted on the three levels. The photosynthetic photon flux density (PPFD) was recorded, and the PPFD values were then converted to the daily light integral (DLI). Plant height and canopy width were measured three times at 14, 21 and 28 days after transplanting. At maturity, fresh weight (FW) was directly monitored after harvest.
UNASSIGNED: The results showed that the highest PPFD and DLI values were found at the upper level (PPFD 697 μmol m-2 s-1 and DLI 29 mol m-2 d-1) in comparison to the middle (PPFD 391 μmol m-2 s-1 and DLI 16 mol m-2 d-1) and lower (PPFD 322 μmol m-2 s-1 and DLI 13 mol m-2 d-1) levels. The lowest plant height and canopy width values were observed on the upper levels for both lettuce varieties during the three measurement dates. The middle (\'Baby Cos\' = 123.8 g plant-1 and \'Green Oak\' = 190.7 g plant-1) and lower (\'Baby Cos\' = 92.9 g plant-1 and \'Green Oak\' = 203.7 g plant-1) levels had the higher values of FW in comparison to the upper level (\'Baby Cos\' = 84.5 g plant-1 and \'Green Oak\' = 97.3 g plant-1). The values of light use efficiency (LUE) showed an increased trend from the upper to lower levels in both varieties, with values of \'Baby Cos\' of 0.10 g mol-1 in the upper level, 0.28 g mol-1 in the middle level and 0.26 g mol-1 in the lower level and \'Green Oak\' of 0.12 g mol-1 in the upper level, 0.44 g mol-1 in the middle level and 0.57 g mol-1 in the lower level. The findings of the study indicated the viability of utilizing vertical shelves for lettuce production.

Crop breeding in sub-Saharan Africa has made considerable gains; however, postharvest and food-related preferences have been overlooked, in addition to how these preferences vary by gender, social difference and context. This context is changing as participatory approaches using intersectional gender and place-based methods are beginning to inform how breeding programmes make decisions. This article presents an innovative methodology to inclusively and democratically prioritise food quality traits of root, tuber and banana crops based on engagement with food systems actors and transdisciplinary collaboration. The outcome of the methodology is the Gendered Food Product Profile (GFPP) - a list of prioritised food quality characteristics - to support breeders to make more socially inclusive decisions on the methods for trait characterisation to select genotypes closer to the needs of food system actors. This article reviews application of the methodology in 14 GFPPs, presents illustrative case studies and lessons learned. Key lessons are that the transdisciplinary structure and the key role of social scientists helped avoid reductionism, supported co-learning, and the creation of GFPPs that represented the diverse interests of food system actors, particularly women, in situ. The method partially addressed power dynamics in multidisciplinary decision making; however, effectiveness was dependent on equitable team relations and supportive institutions committed to valuing plural forms of knowledge. Actions to address power asymmetries that privilege particular types of knowledge and voices in decision making are crucial in techno-science projects, along with opportunities for co-learning and long-term collaboration and a transdisciplinary structure at higher level. © 2024 The Authors. Journal of The Science of Food and Agriculture published by John Wiley & Sons Ltd on behalf of Society of Chemical Industry.

OBJECTIVE: Plant breeders are increasingly turning to crop wild relatives (CWRs) to ensure food security in a rapidly changing environment. However, CWR populations are confronted with various human-induced threats, including hybridization with their nearby cultivated crops. This might be a particular problem for wild coffee species, which often occur near coffee cultivation areas. Here, we briefly review the evidence for wild Coffea arabica (cultivated as Arabica coffee) and Coffea canephora (cultivated as Robusta coffee) and then focused on C. canephora in the Yangambi region in the Democratic Republic of the Congo. There, we examined the geographical distribution of cultivated C. canephora and the incidence of hybridization between cultivated and wild individuals within the rainforest.
METHODS: We collected 71 C. canephora individuals from home gardens and 12 C. canephora individuals from the tropical rainforest in the Yangambi region and genotyped them using genotyping-by-sequencing (GBS). We compared the fingerprints with existing GBS data from 388 C. canephora individuals from natural tropical rainforests and the INERA Coffee Collection, a Robusta coffee field gene bank and the most probable source of cultivated genotypes in the area. We then established robust diagnostic fingerprints that genetically differentiate cultivated from wild coffee, identified cultivated-wild hybrids and mapped their geographical position in the rainforest.
RESULTS: We identified cultivated genotypes and cultivated-wild hybrids in zones with clear anthropogenic activity, and where cultivated C. canephora in home gardens may serve as a source for crop-to-wild gene flow. We found relatively few hybrids and backcrosses in the rainforests.
CONCLUSIONS: The cultivation of C. canephora in close proximity to its wild gene pool has led to cultivated genotypes and cultivated-wild hybrids appearing within the natural habitats of C. canephora. Yet, given the high genetic similarity between the cultivated and wild gene pool, together with the relatively low incidence of hybridization, our results indicate that the overall impact in terms of risk of introgression remains limited so far.

Co-occurrence a correlation profiles are driven by different factors (exogenous and endogenous) and drawing a profile of association between species based on co-occurrence, without assessing how these species vary in terms of ecological niche can lead to wrong conclusions. The objective was to determine the co-occurrence and correlation patterns of phytophagous insects in canola crop and to evaluate how these patterns varied according to the crop stage (phenology-biotic) and sowing times (agricultural practice-abiotic). We found that the patterns of co-occurrence and correlation between species were reflections of population variations due to the phenology and sowing times of canola. Variations in the multi-species abundance matrix were influenced by mean air temperature and accumulated rainfall. The main species associated with canola in southern Brazil, in terms of abundance, were P. xylostella, D. speciosa, and N. viridula. These species were mostly negatively associated. When evaluating their population variations, we found that they explore different temporal niches, whether in terms of phenology or sowing times. Finally, we demonstrate empirically that despite being important, association patterns based on co-occurrence and correlation should be interpreted in light of the understanding of patterns of niche exploitation and temporal variation of species.