Agricultural ecosystems provide humans with food, forage, bioenergy and pharmaceuticals and are essential to human wellbeing. These systems rely on ecosystem services provided by natural ecosystems, including pollination, biological pest control, maintenance of soil structure and fertility, nutrient cycling and hydrological services. Preliminary assessments indicate that the value of these ecosystem services to agriculture is enormous and often underappreciated. Agroecosystems also produce a variety of ecosystem services, such as regulation of soil and water quality, carbon sequestration, support for biodiversity and cultural services. Depending on management practices, agriculture can also be the source of numerous disservices, including loss of wildlife habitat, nutrient runoff, sedimentation of waterways, greenhouse gas emissions, and pesticide poisoning of humans and non-target species. The tradeoffs that may occur between provisioning services and other ecosystem services and disservices should be evaluated in terms of spatial scale, temporal scale and reversibility. As more effective methods for valuing ecosystem services become available, the potential for 'win-win' scenarios increases. Under all scenarios, appropriate agricultural management practices are critical to realizing the benefits of ecosystem services and reducing disservices from agricultural activities.

Digital agriculture employs artificial intelligence (AI) to transform data collected in the field into actionable crop management. Effective digital agriculture models can detect problems early, reducing costs significantly. However, ineffective models can be counterproductive. Farmers often want to validate models by spot checking their fields before expending time and effort on recommended actions. However, in large fields, farmers can spot check too few areas, leading them to wrongly believe that ineffective models are effective. Model validation is especially difficult for models that use neural networks, an AI technology that normally assesses crops health accurately but makes inexplicable recommendations. We present a new approach that trains random forests, an AI modeling approach whose recommendations are easier to explain, to mimic neural network models. Then, using the random forest as an explainable white box, we can (1) gain knowledge about the neural network, (2) assess how well a test set represents possible inputs in a given field, (3) determine when and where a farmer should spot check their field for model validation, and (4) find input data that improve the test set. We tested our approach with data used to assess soybean defoliation. Using information from the four processes above, our approach can reduce spot checks by up to 94%.

Agriculture occupies 38% of the planet's terrestrial surface, using 70% of freshwater resources. Its modern practice is dominated by an industrial-productivist discourse, which has contributed to the simplification and degradation of human and ecological systems. As such, agricultural transformation is essential for creating more sustainable food systems. This paper focuses on discursive change. A prominent discursive alternative to industrial-productivist agriculture is regenerative agriculture. Regenerative discourses are emergent, radically evolving and diverse. It is unclear whether they have the potential to generate the changes required to shift industrial-productivist agriculture. This paper presents a literature-based discourse analysis to illustrate key thematic characteristics of regenerative agricultural discourses. The analysis finds that such discourses: situate agricultural work within nested, complex living systems; position farms as relational, characterised by co-evolution between humans and other landscape biota; perceive the innate potential of living systems as place-sourced; maintain a transformative openness to alternative thinking and practice; believe that multiple regenerative cultures are necessary for deeply regenerative agriculture; and depart from industrialism to varying degrees. The paper concludes by reviewing three transformative opportunities for regenerative discourses-discourse coalitions, translocal organising and collective learning.

Ecosystems provide multiple services to humans. However, agricultural systems are usually evaluated on their productivity and economic performance, and a systematic and quantitative assessment of the multifunctionality of agroecosystems including environmental services is missing. Using a long-term farming system experiment, we evaluated and compared the agronomic, economic, and ecological performance of the most widespread arable cropping systems in Europe: organic, conservation, and conventional agriculture. We analyzed 43 agroecosystem properties and determined overall agroecosystem multifunctionality. We show that organic and conservation agriculture promoted ecosystem multifunctionality, especially by enhancing regulating and supporting services, including biodiversity preservation, soil and water quality, and climate mitigation. In contrast, conventional cropping showed reduced multifunctionality but delivered highest yield. Organic production resulted in higher economic performance, thanks to higher product prices and additional support payments. Our results demonstrate that different cropping systems provide opposing services, enforcing the productivity-environmental protection dilemma for agroecosystem functioning.

Providing economic opportunities for youth in agriculture is essential to securing the future of agriculture in Africa, addressing poverty, unemployment, and inequality. However, barriers limit youth participation in agriculture and the broader food system. This scoping review aimed to investigate the opportunities and challenges for youth in participating in agriculture and the food system in Africa. This review conducted a scoping review using the PRISMA guideline. Published studies were retrieved from online databases (Web of Science, Cab Direct, and Science Direct) for 2009 to 2019. The findings showed that existing agricultural interventions are production-centric and provide low-income earnings and inadequate social protection. We also found that the youth have pessimistic perceptions about agriculture's capability of improving their living standards. This could be ascribed to the minimal youth involvement in agricultural activities and the youth's shared understanding of the agricultural sector's contribution to general economic growth. From a policy perspective, the literature revealed that current agricultural development programs do not adequately address structural issues underpinning youth participation in the economy. Therefore, to enhance the involvement of youths in agriculture, there is a need for policy implementation in the area of integrated agricultural-based interventions that are context-specific and promote meaningful youth participation in shaping future food systems.

Replacement of crop landraces by modern varieties is thought to cause diversity loss. We studied genetic erosion in maize within a model system; modernized smallholder agriculture in southern Mexico. The local seed supply was described through interviews and in situ seed collection. In spite of the dominance of commercial seed, the informal seed system was found to persist. True landraces were rare and most informal seed was derived from modern varieties (creolized). Seed lots were characterized for agronomical traits and molecular markers. We avoided the problem of non-consistent nomenclature by taking individual seed lots as the basis for diversity inference. We defined diversity as the weighted average distance between seed lots. Diversity was calculated for subsets of the seed supply to assess the impact of replacing traditional landraces with any of these subsets. Results were different for molecular markers, ear- and vegetative/flowering traits. Nonetheless, creolized varieties showed low diversity for all traits. These varieties were distinct from traditional landraces and little differentiated from their ancestral stocks. Although adoption of creolized maize into the informal seed system has lowered diversity as compared to traditional landraces, genetic erosion was moderated by the distinct features offered by modern varieties.

Agriculture is one of the most hazardous economic sectors, and it accounts for many accidents and occupational diseases every year. In Italy, about one-third of injuries involve the upper extremity, with long-term consequences for the workers and economic damage for agricultural companies and farms. This systematic review describes upper limb injuries among farmworkers, especially hand injuries, and highlights the main dangerous risk factors. Literature review included articles published in the major databases (PubMed, Cochrane Library, Scopus), using a combination of some relevant keywords. This online search yielded 951 references; after selection, the authors analyzed 53 articles (3 narrative reviews and 50 original articles). From this analysis, it appears that younger male farmers are mostly involved, especially in the harvesting season. The upper limb and hand are often the body parts that sustain most damage as these are mostly involved in driving tractors or tools. The most frequent type of lesions are open wounds, lacerations, fractures, strains, and overexertion lesions. Sometimes, a distracting element (such as mobile phone use, quarrels, working hours load) is present; poor use of protective devices and lack of safety design in tools can also increase the risk of accidents. For these reasons, in the agricultural sector, a system of health promotion and good practices is needed to promote workers' awareness of the sources of risk, highlight more dangerous situations and apply organizational behavioral measures.

We present an end-to-end smart harvesting solution for precision agriculture. Our proposed pipeline begins with yield estimation that is done through the use of object detection and tracking to count fruit within a video. We use and train You Only Look Once model (YOLO) on video clips of apples, oranges and pumpkins. The bounding boxes obtained through objection detection are used as an input to our selected tracking model, DeepSORT. The original version of DeepSORT is unusable with fruit data, as the appearance feature extractor only works with people. We implement ResNet as DeepSORT's new feature extractor, which is lightweight, accurate and generically works on different fruits. Our yield estimation module shows accuracy between 91-95% on real footage of apple trees. Our modification successfully works for counting oranges and pumpkins, with an accuracy of 79% and 93.9% with no need for training. Our framework additionally includes a visualization of the yield. This is done through the incorporation of geospatial data. We also propose a mechanism to annotate a set of frames with a respective GPS coordinate. During counting, the count within the set of frames and the matching GPS coordinate are recorded, which we then visualize on a map. We leverage this information to propose an optimal container placement solution. Our proposed solution involves minimizing the number of containers to place across the field before harvest, based on a set of constraints. This acts as a decision support system for the farmer to make efficient plans for logistics, such as labor, equipment and gathering paths before harvest. Our work serves as a blueprint for future agriculture decision support systems that can aid in many other aspects of farming.

Bread wheat landraces were an important source of biodiversity used in agriculture before the widespread adoption of high-yielding commercial cultivars adapted to high inputs. Could future agriculture exploit these landraces in different cropping systems in organic or lower-input environments? A two-year field trial was conducted to evaluate grain yield, agronomic performance, and grain quality of bread wheat landraces under different cropping systems, including low-input/organic/conventional environments. Significant variability was found for almost all characteristics among landraces, which makes landraces valuable sources of genetic variation for breeding programs aimed at achieving high and consistent production as well as high-quality products in low-input/organic environments. Additionally, landraces play a crucial role in expanding the genetic diversity of cultivated bread wheat and mitigating biodiversity erosion, thereby enabling crops to better withstand the challenges of low-input/organic agriculture. The landrace "Xilokastro Lamias" had the highest yield among the landraces evaluated in the first growing season (2.65 t·ha-1) and one of the highest yields (2.52 t·ha-1) of all genotypes in the second growing season, which shows promising potential as a starting material in breeding programs targeting high and stable yields. GGE biplot analysis identified the landrace "Xilokastro Lamias", along with commercial cultivars "Yecora E" and "Panifor", as suitable candidates for direct use in low-input/organic wheat farming systems to achieve enhanced productivity. In the conventional environment (C2-IPGRB), commercial cultivars showed the highest values (3.09 to 3.41 ton·ha-1). Of the landraces, only the X4 showed a high GY (3.10 ton·ha-1) while the other landraces had ~33-85% lower yield. In the organic environment (O2-IPGRB), the highest productivity was found in the commercial cultivar X5 and the landrace X4. Commercial cultivars X8 and X7 showed ~68% reduction in GY in the organic environment compared to the conventional, while this reduction was half for the landraces. Finally, the reduction in grain yield between conventional and organic environments was observed to be 45% for commercial cultivars, while it was only half for landraces. This finding confirms the adaptability of landraces to organic agriculture.

Enhancing global food security by increasing the productivity of green revolution varieties of cereals risks increasing the collateral environmental damage produced by inorganic nitrogen fertilizers. Improvements in the efficiency of nitrogen use of crops are therefore essential; however, they require an in-depth understanding of the co-regulatory mechanisms that integrate growth, nitrogen assimilation and carbon fixation. Here we show that the balanced opposing activities and physical interactions of the rice GROWTH-REGULATING FACTOR 4 (GRF4) transcription factor and the growth inhibitor DELLA confer homeostatic co-regulation of growth and the metabolism of carbon and nitrogen. GRF4 promotes and integrates nitrogen assimilation, carbon fixation and growth, whereas DELLA inhibits these processes. As a consequence, the accumulation of DELLA that is characteristic of green revolution varieties confers not only yield-enhancing dwarfism, but also reduces the efficiency of nitrogen use. However, the nitrogen-use efficiency of green revolution varieties and grain yield are increased by tipping the GRF4-DELLA balance towards increased GRF4 abundance. Modulation of plant growth and metabolic co-regulation thus enables novel breeding strategies for future sustainable food security and a new green revolution.

The digital transformation of agriculture has evolved various aspects of management into artificial intelligent systems for the sake of making value from the ever-increasing data originated from numerous sources. A subset of artificial intelligence, namely machine learning, has a considerable potential to handle numerous challenges in the establishment of knowledge-based farming systems. The present study aims at shedding light on machine learning in agriculture by thoroughly reviewing the recent scholarly literature based on keywords' combinations of "machine learning" along with "crop management", "water management", "soil management", and "livestock management", and in accordance with PRISMA guidelines. Only journal papers were considered eligible that were published within 2018-2020. The results indicated that this topic pertains to different disciplines that favour convergence research at the international level. Furthermore, crop management was observed to be at the centre of attention. A plethora of machine learning algorithms were used, with those belonging to Artificial Neural Networks being more efficient. In addition, maize and wheat as well as cattle and sheep were the most investigated crops and animals, respectively. Finally, a variety of sensors, attached on satellites and unmanned ground and aerial vehicles, have been utilized as a means of getting reliable input data for the data analyses. It is anticipated that this study will constitute a beneficial guide to all stakeholders towards enhancing awareness of the potential advantages of using machine learning in agriculture and contributing to a more systematic research on this topic.

A spatiotemporal analysis on the changes in the marsh landscape in the Honghe National Nature Reserve, a Ramsar reserve, and the surrounding farms in the core area of the Sanjiang Plain during the past 30 years was conducted by integrating field survey work with remote sensing techniques. The results indicated that intensified agricultural development had transformed a unique natural marsh landscape into an agricultural landscape during the past 30 years. Ninety percent of the natural marsh wetlands have been lost, and the areas of the other natural landscapes have decreased very rapidly. Most dry farmland had been replaced by paddy fields during the progressive change of the natural landscape to a farm landscape. Attempts of current Chinese institutions in preserving natural wetlands have achieved limited success. Few marsh wetlands have remained healthy, even after the establishment of the nature reserve. Their ecological qualities have been declining in response to the increasing threats to the remaining wetland habitats. Irrigation projects play a key role in such threats. Therefore, the sustainability of the natural wetland ecosystems is being threatened by increased regional agricultural development which reduced the number of wetland ecotypes and damaged the ecological quality.

In the pursuit of optimizing the efficiency, flexibility, and adaptability of agricultural practices, human-robot interaction (HRI) has emerged in agriculture. Enabled by the ongoing advancement in information and communication technologies, this approach aspires to overcome the challenges originating from the inherent complex agricultural environments. Τhis paper systematically reviews the scholarly literature to capture the current progress and trends in this promising field as well as identify future research directions. It can be inferred that there is a growing interest in this field, which relies on combining perspectives from several disciplines to obtain a holistic understanding. The subject of the selected papers is mainly synergistic target detection, while simulation was the main methodology. Furthermore, melons, grapes, and strawberries were the crops with the highest interest for HRI applications. Finally, collaboration and cooperation were the most preferred interaction modes, with various levels of automation being examined. On all occasions, the synergy of humans and robots demonstrated the best results in terms of system performance, physical workload of workers, and time needed to execute the performed tasks. However, despite the associated progress, there is still a long way to go towards establishing viable, functional, and safe human-robot interactive systems.

Climate change during the last 40 years has had a serious impact on agriculture and threatens global food and nutritional security. From over half a million plant species, cereals and legumes are the most important for food and nutritional security. Although systematic plant breeding has a relatively short history, conventional breeding coupled with advances in technology and crop management strategies has increased crop yields by 56 % globally between 1965-85, referred to as the Green Revolution. Nevertheless, increased demand for food, feed, fiber, and fuel necessitates the need to break existing yield barriers in many crop plants. In the first decade of the 21st century we witnessed rapid discovery, transformative technological development and declining costs of genomics technologies. In the second decade, the field turned towards making sense of the vast amount of genomic information and subsequently moved towards accurately predicting gene-to-phenotype associations and tailoring plants for climate resilience and global food security. In this review we focus on genomic resources, genome and germplasm sequencing, sequencing-based trait mapping, and genomics-assisted breeding approaches aimed at developing biotic stress resistant, abiotic stress tolerant and high nutrition varieties in six major cereals (rice, maize, wheat, barley, sorghum and pearl millet), and six major legumes (soybean, groundnut, cowpea, common bean, chickpea and pigeonpea). We further provide a perspective and way forward to use genomic breeding approaches including marker-assisted selection, marker-assisted backcrossing, haplotype based breeding and genomic prediction approaches coupled with machine learning and artificial intelligence, to speed breeding approaches. The overall goal is to accelerate genetic gains and deliver climate resilient and high nutrition crop varieties for sustainable agriculture.

Small RNA (sRNA) has become an alternate biotechnology tool for sustaining eco-agriculture by enhancing plant solidity and managing environmental hazards over traditional methods. Plants synthesize a variety of sRNA to silence the crucial genes of pests or plant immune inhibitory proteins and counter adverse environmental conditions. These sRNAs can be cultivated using biotechnological methods to apply directly or through bacterial systems to counter the biotic stress. On the other hand, through synthesizing sRNAs, microbial networks indicate toxic elements in the environment, which can be used effectively in environmental monitoring and management. Moreover, microbes possess sRNAs that enhance the degradation of xenobiotics and maintain bio-geo-cycles locally. Selective bacterial and plant sRNA systems can work symbiotically to establish a sustained eco-agriculture system. An sRNA-mediated approach is becoming a greener tool to replace xenobiotic pesticides, fertilizers, and other chemical remediation elements. The review focused on the applications of sRNA in both sustained agriculture and bioremediation. It also discusses limitations and recommends various approaches toward future improvements for a sustained eco-agriculture system.

Agricultural land covers approximately 40% of Earth's land surface and affects hydromorphological, biogeochemical and ecological characteristics of fluvial networks. In the northern temperate region, agriculture also strongly affects the amount and molecular composition of dissolved organic matter (DOM), which constitutes the main vector of carbon transport from soils to fluvial networks and to the sea, and is involved in a large variety of biogeochemical processes. Here, we provide first evidence about the wider occurrence of agricultural impacts on the concentration and composition of fluvial DOM across climate zones of the northern and southern hemispheres. Both extensive and intensive farming altered fluvial DOM towards a more microbial and less plant-derived composition. Moreover, intensive farming significantly increased dissolved organic nitrogen (DON) concentrations. The DOM composition change and DON concentration increase differed among climate zones and could be related to the intensity of current and historical nitrogen fertilizer use. As a result of agriculture intensification, increased DON concentrations and a more microbial-like DOM composition likely will enhance the reactivity of catchment DOM emissions, thereby fuelling the biogeochemical processing in fluvial networks, and resulting in higher ecosystem productivity and CO2 outgassing.

The Water-Food Nexus (WF) has been proposed to reach equitable, balanced, and sustainable access to water and food resources in the face of the growing population demand. Therefore, developing models to assess them has become more relevant. This work systematically reviews the literature on the tools used to evaluate water and food resources between 2002 and 2020. Furthermore, it reports a critical analysis of the software used to assess the WF Nexus quantitatively. The models analyzed were Life Cycle Assessment (LCA), Common Agricultural Policy Regional Impact (CAPRI), Global Food and Water System (GFWS), Soil and Water Assessment Tool (SWAT), Water Evaluation And Planning system (WEAP), and Soil Water Atmosphere Plant (SWAP). We deduced that the following are necessary in evaluating the WF Nexus: (1) the capacity to generate future scenarios, (2) a global application, and (3) the application in case studies. The present paper is the first review to provide an overview of the software applied to evaluate WF Nexus, including the advantages and disadvantages of the tools found. They can help build sustainability criteria when designing policies that reduce water and food security risks and promote efficient water and food use.

Plant nutrition plays a central role in the global challenges to produce sufficient and nutritious food, lessen rural poverty, and reducing the environmental footprint of farming. Site-specific nutrient management (SSNM) provides field-specific solutions for smallholder farmers, potentially creating co-benefits of increased productivity and sustainability. Here we perform the first meta-analysis comparing SSNM with farmers' fertilizer practice for maize, rice and wheat using 61 published papers across 11 countries. Relative to the farmer practice, across all crops SSNM increased grain yield by 12% and profitability by 15% with 10% less fertilizer nitrogen applied, thereby improving nitrogen use efficiency and reducing nitrogen pollution to the environment. Delivering it to millions of smallholder farmers requires use of digital decision support tools, but also policy incentives, links with financial and input supply services, and enhancing public-private partnerships.

There is a dearth of literature that provides a bibliometric analysis concerning the role of Artificial Intelligence (AI) in sustainable agriculture therefore this study attempts to fill this research gap and provides evidence from the studies conducted between 2000-2021 in this field of research. The study is a systematic bibliographic analysis of the 465 previous articles and reviews done between 2000-2021 in relation to the utilization of AI in sustainable methods of agriculture. The results of the study have been visualized and presented using the VOSviewer and Biblioshiny visualizer software. The results obtained post analysis indicate that, the amount of academic works published in the field of AI's role in enabling sustainable agriculture increased significantly from 2018. Therefore, there is conclusive evidence that the growth trajectory shows a significant climb upwards. Geographically analysed, the country collaboration network highlights that most number of studies in the realm of this study originate from China, USA, India, Iran, France. The co-author network analysis results represent that there are multi-disciplinary collaborations and interactions between prominent authors from United States of America, China, United Kingdom and Germany. The final framework provided from this bibliometric study will help future researchers identify the key areas of interest in research of AI and sustainable agriculture and narrow down on the countries where prominent academic work is published to explore co-authorship opportunities.

Plants contain diverse microbial communities. The associated microorganisms confer advantages to the host plant, which include growth promotion, nutrient absorption, stress tolerance, and pathogen and disease resistance. In this review, we explore how agriculture is implementing the use of microbial inoculants (single species or consortia) to improve crop yields, and discuss current strategies to study plant-associated microorganisms and how their diversity varies under unconventional agriculture. It is predicted that microbial inoculation will continue to be used in agriculture.