Search

Small companies encounter difficulties to adapt to new markets with a sustainable perspective. The subject of this article is a paper transformation company which has been eager to develop the organic farming market by developing a new plant support. Alternatives made from plant fibres or plastics exist, such as jute and polypropylene. The main difficulty of this project was to ecodesign a paper product with a multicriteria approach. The factors considered have been divided into two categories. Firstly, the environmental impacts calculated according to the Life Cycle Assessment methodology (on raw material extraction, manufacturing and end-of-life) are summarised. Secondly, the characteristics of the product are discussed in regards to these results and sustainability questions as part of the interpretation phase. Finally, ways of improvement of the LCA methodology to improve the study in terms of geographical representativeness and societal considerations are discussed. [ABSTRACT FROM AUTHOR]

As one of the essential trace elements in life activities, copper ion (Cu2+) plays a very important role in human health. However, copper-containing pesticides are usually used for sterilization and disinfestation in agriculture. Thus, the residues of copper-containing pesticides in agricultural samples increase the risk of excessive intake of Cu2+ for human. The development of an effective method for detecting Cu2+ is still an important task. Herein, a detecting system based on AuNCs@ZIF-8 modified paper and smartphone platform was developed for visual detection of Cu2+ in agricultural samples. Herein, a detecting system based on AuNCs@ZIF-8 modified paper and smartphone platform was developed for visual detection of Cu2+ in agricultural samples. In the detecting system, gold nanoclusters (AuNCs) were packaged by ZIF-8 to limit their molecular motion and enhance the fluorescence effectively. In the meanwhile, by ultrasound-assisted biomimetic mineralizing, AuNCs@ZIF-8 composites were uniformly synthesized in situ on the surface of the paper fibers to indicate Cu2+ by fluorescence quenching. A portable visual monitoring system consisted of the prepared Cu2+ paper sensor and a smartphone platform was then successfully built and applied to on site detecting Cu2+ in agricultural samples. The limit of detection (LOD) was 4.57 μM and recovery rate varied from 96.50 % to 121.58 %. The developed detecting system for Cu2+ has the advantages of easy preparation and operation, and is very suitable for the use in agricultural products and farmland. [Display omitted] • Ultrasound-assisted biomimetic mineralization was used to fabricate paper sensor. • AuNCs@ZIF-8 was modified uniformly on paper fibers to indicate Cu2+ in-situ. • A portable visual monitoring system was constructed with paper sensor and smartphone. • Cu2+ visual detection in samples of Cu2+ solution and agricultural products. [ABSTRACT FROM AUTHOR]

• Reviewed "precision agriculture", "smart agriculture" and "digital agriculture" concepts. • Suggested "smart agriculture" and "digital agriculture" be phases of "precision agriculture". • Proposed a few research focuses on smart and digital technologies for agriculture. [ABSTRACT FROM AUTHOR]

Summary: This paper uses data from the 2003/04 Cambodia Household Socioeconomic Survey to investigate the effects of property rights to land. Plots held with a paper documenting ownership in rural Cambodia are found to have higher productivity and land values than other plots, while property rights have weak effects on access to credit. The paper also investigates whether the introduction of private property rights leads to decreased availability of common property resources. The data offers only weak support for this hypothesis. The general insight is that policies to strengthen land property rights can have important, positive effects on the rural economy, even in an environment of low state capacity. [Copyright &y& Elsevier]

This paper analyses farmers’ networking strategies for sustainable agricultural development. The focus is on internal barriers of farmers’ networks with respect to the management of the group and collective learning processes. These aspects determine to an extent the success or failure of collective strategies. Based upon case study material we will draw lessons and present ideas on how management and learning can be enhanced. We argue that in collective strategies the focus should not only be on the goal of the group, but that attention to the process of cooperation such as safeguarding coherence, monitoring and evaluation of goals and views, shared responsibility and balanced leadership is a prerequisite for effective collective action. [Copyright &y& Elsevier]

Although Australia's population is concentrated in major urban centres along its coastal fringe, its less populous rural communities are important to society and the economy—supporting sectors like agriculture, which occupies over half the continent's land mass and accounts for 2.2% of value added gross domestic product (GDP) (Jackson et al., 2020). The vast distances between urban and rural centres present challenges to the provision of essential infrastructure like roads, transport, energy – and telecommunications. Within this last category, internet connectivity and skills are both increasingly necessary and historically less available to the regional and rural agricultural sector in comparison to other industries and geographic communities. The digital inclusion agenda in Australia aims to address such gaps by promoting and supporting people and communities to use technology to improve social and economic well-being. This article builds on research underpinning the Australian Digital Inclusion Index (ADII), which defines digital inclusion as the capacity of people to access , afford and use online technologies effectively. The article focuses on the nature and extent of digital inclusion for Australia's farmers (identified as farmers and farm managers) based on analysis of a customised set of primary data extracted from the ADII dataset. This analysis reveals generally low levels of digital inclusion in rural communities, particularly among farmers, with distinctive and complex characteristics across measures of Access, Affordability and Digital Ability. Our findings highlight a perplexing scenario in which farmers score poorly on the Index when compared to Australians who live in similar circumstances but are not employed in the farming sector. We attribute lower levels of access to limited internet technology options, lower data speeds, inadequate reliability and lower data allowances. Less affordability is associated with individual-level socioeconomic factors, along with lack of competition between service providers in sparse population areas, the comparative cost of building telecommunications infrastructure in the bush, and the need for redundancy in rural and remote solutions. Finally, lower digital ability scores reflect social, cultural and material practices on farms that have produced distinctive orientations to technology. We conclude the article by explaining the contributions of the paper to digital inclusion research and by making recommendations for policy development. • Farmers in rural Australia have low levels of digital inclusion across access, affordability and digital ability. • Low access and affordability may be attributed to insufficient internet infrastructure and limited technology and data. • Low ability may be attributed to demographic factors and social, economic and material practices. • Governments and industry should consider the development of digital skills programs tailored for the farming sector. [ABSTRACT FROM AUTHOR]

Abstract: Stable isotopic measurements (δ 15N and δ 18O), combined with hydrochemical assessment, were used to elucidate the chemical quality of groundwater and the sources of nitrate (NO3 −) in the groundwater in an agricultural region at Huzhou City, China. Paddy rice (Zhejing 41) and vegetables (Chinese cabbage) are the typical crops grown in the study area. The chemical properties of groundwater in the study area were controlled using natural geochemical processes and anthropogenic activities. The results show that SO4 2− and NH4 + were the major contaminants. Surficial conditions influenced the shallow groundwater. However, no relationship between the ion concentration in groundwater and well depth was found. The combined use of isotopes was useful for identifying NO3 − sources. The isotopic values for δ 15N and δ 18O ranged from −0.8‰ to 20.8‰ and from −2.0‰ to 18.8‰, respectively. The isotopic data were definitive and revealed that N-fertilizer, soil organic matter, and manure dominated the sources of NO3 − in the study area. The δ 15N and δ 18O data for NO3 − indicated a significant degree of nitrification and a lesser extent of denitrification in the agricultural area. Spatial variations in δ 15N for NO3 − showed that NO3 − concentration and δ 15N values in the upper groundwater (<200cm) were higher than the values in the lower groundwater (>200cm). [Copyright &y& Elsevier]

Abstract: In agricultural soil, a suite of anthropogenic events shape the ecosystem processes and populations. However, the impact from anthropogenic sources on the soil environment is almost exclusively assessed for chemicals, although other factors like crop and tillage practices have an important impact as well. Thus, the farming system as a whole should be evaluated and ranked according to its environmental benefits and impacts. Our starting point is a data set describing agricultural events and soil biological parameters. Using machine learning methods for inducing regression and model trees, we produce empirical models able to predict the soil quality from agricultural measures in terms of quantities describing the soil microarthropod community. We are also interested in discovering additional higher level knowledge. In particular, we have identified the most important factors influencing the population densities of springtails and mites and their biodiversity. We also identify to which agricultural actions different microarthropods react distinctly. To obtain this higher level knowledge, we employ multi-objective regression trees. [Copyright &y& Elsevier]

Extensively used agricultural mulch fabricated from nonbiodegradable polyolefin plastic causes tremendous environmental pollution. In this work, a paper-based mulch, composed of the cellulose fiber networks incorporated with Emamectin benzoate (EB)@sodium lignosulfonate (SL), has been developed with facile papermaking/coating methods. The spherical microcapsule loaded with pesticide EB has a desirable core-shell structure for better protection and sustained release of photosensitive EB. The loading rate and encapsulation efficiency reached 78.5 % and 52.3 %, respectively. Furthermore, microcapsules exhibited excellent slow-release behavior and resistance to photolysis. Natural carnauba wax was coated on the surface of the paper-based mulch to form a hydrophobic layer and increase the physical intertwinement of fibers in the mulch, thereby exhibiting superior performance, such as enhanced tensile strength, excellent hydrophobicity, high air permeability, and high light transmittance at reasonable level. Moreover, unlike conventional polyethylene mulch film, the functionalized paper-based mulch almost completely biodegraded after 75 days in the soil. Thus, multifunctional, eco-friendly mulch from lignocellulose is an innovative approach to obtaining the sustained release of agrochemicals, and it provides an excellent alternative to conventional agricultural plastic mulch. [ABSTRACT FROM AUTHOR]

There is an increased interest for finding strains able to contribute to plant nutrition and health, since these are desirable for the formulation of agricultural bioinoculants. Obtaining a safe and efficient product requires exhaustive evaluations from which most methods used for this purpose involve the use of substrates or are established under uncontrolled conditions, so that various factors can mask the results of the plant-microorganism interaction. In vitro methods mostly involve the use of Petri Dishes (PD) but limit the results to seed germination. Other methods of germination involve the use of acrylic boxes (GB) allowing for better plant development, but are little known. Methods such as ISTA are widely used to evaluate the physiological quality of seeds in productive terms. Despite their efficiency, these methods have not been previously used to evaluate the effect of plant-microorganism interaction on crops. In the present study, modifications were made to the germination between paper of ISTA (BP) method, and were compared to the PD anf GB methods to evaluate the impact of the bacterium Serratia liquefaciens 385 and the yeast Clavispora lusitaniae Y35 on maize, bean and squash. Through the evaluation of physiological parameters in seed and seedling, the results clearly showed the superiority of the BP method to evaluate the effect of microorganisms since it allows observing a better development in the seedlings in terms of growth of the plumule, a better architecture of the radical system in which the emergence of adventitious secondary roots and differentiated radical hairs is observed in comparison with seedlings obtained under the other methods. Similarly, it was possible to observe the different effects on each of the three crops with respect to the inoculation of the bacteria and yeast. These results were significantly better in seedlings obtained in the BP method independently of the type of crop evaluated, considering the BP method suitable to be applied in large-scale bioprospecting plant-growth-promoting microorganism studies. • Fast and simple evaluations of plant growth-promoting microbial strains on plants. • Large-scale bioprospecting studies of microbial strains to develop bioinoculants. • Between paper ISTA germination method show significantly better results despite the seed crop. [ABSTRACT FROM AUTHOR]

This paper focuses on the first human settlement of the Kohgiluyeh region in southwestern Iran in relation to regional environmental conditions. At an altitude between 500 and 3500 m asl, a range of different ecozones and diversified resources available at short distance compose this highly mountainous region. The first sedentary occupation occurred here during the 8th millennium BC. Applying remote sensing, GIS and geo-topographic landscape analyses to contextualize the available dataset, our study illustrates that in the southern portion of the region fertile lands played a pivotal role for the first settled communities and the stability of their subsistence strategies. Farming became even more important during the later Neolithic phase. Furthermore, Neolithic sites are recorded along the bottom of open slopes, at locations with direct access to the combined resources of the plains and the hilly lands. The first occupation of the region is also documented at high elevation up to 1600 m asl, along narrow valley formations, where limited areas are available for farming. [ABSTRACT FROM AUTHOR]

This paper examines the effects of exchange and capital restrictions on trade and compares them with those associated with trade restrictions. Our main result is that capital account restrictions have large and statistically significant effects on trade flows. Such effects are smaller than those from trade restrictions, however. The effects of exchange and capital restrictions are larger for trade in goods, especially for agriculture and manufacturing, and smaller for trade in services. [ABSTRACT FROM AUTHOR]

Sulfur dioxide (SO 2) is one of the main harmful gas in agricultural greenhouse. Its concentration can effectively reflect the health status of plants in agricultural greenhouse. In this paper, the adsorption characteristics of SO 2 on modified graphene-based were studied in comparison. The adsorption models of epoxy grouped graphene (G-O), palladium doped graphene (Pd-G) and epoxy and palladium co-doped graphene (Pd-G-O) to SO 2 were established based on the first-principles, analyzing in terms of adsorption energy, density of states, orbitals, charge density and desorption time of the adsorption models. The results showed that Pd-G-O exhibited strong chemisorption with adsorption energy of -1.237 eV. Furthermore, three modified graphene-based sensing materials were prepared via the redox method in this paper, and their crystal morphology and chemical elemental composition were investigated by transmission electron microscopy (TEM) and X-ray photoelectron spectroscopy (XPS), respectively. The response performance of the graphene-based sensor to SO 2 was tested by a gas-sensitive testbed. The test results confirmed that the response of the Pd-G-O sample to 50 ppm SO 2 at room temperature was 10.5 (1.567 and 1.235 times than that of G-O, Pd-G). Pd-G-O provides theoretical basis and experimental support for the development of a highly sensitive and fast response sensor for the detection of harmful gases in agricultural greenhouse. [ABSTRACT FROM AUTHOR]

Assessment of zooarchaeological data for the principal livestock (i.e., cattle, sheep, goats and pigs) reveals regional and cultural variability in how animals were manipulated, marketed, bred, and utilized over the course of antiquity. This paper focuses upon those developments, as reconstructed through zooarchaeological frequency and morphometric data for the period from c. 1000 BCE to c. 700 CE. Regionally, North Africa encompasses a vast territory, from Egypt, in the East, to Mauretania, in the West. Ecologically, there are variations within each of these zones. Culturally, moreover, these regions witnessed the introduction and influence of different social and economic agents and factors over the timeframe under investigation. This paper examines patterns in these components in a broad synthetic manner, using zooarchaeological data across the entire expanse of Roman North Africa—from Egypt to Mauretania. Focus centers upon the nature and degree of size and shape changes within the principal livestock, modifications that were in part influenced by aspects such as the scale and pattern in trade, dietary appeal for animal products (notably fatty meats), market demands, ecological adaptations, as well as economic and cultural contact among areas. Key similarities and differences in faunal patterns, across time and space within ancient North Africa, and the links these share with changes in animal husbandry schemes are outlined. [ABSTRACT FROM AUTHOR]

This paper examines how a certain threshing machine was developed and improved by Jobst Heinrich Voigt and Gottfried Wilhelm Leibniz between 1699 and 1700. While this machine was based on various mechanical principles and instruments, including the pinned drum mechanism first noted by Georg Philipp Harsdörffer, it was later reconceptualized as a 'mathematical' machine. I claim that such a positioning was not unique to this machine, but part of a wider movement during the 18th century that considered various artisanal instruments as mathematical, as well as agricultural and artisanal knowledge as scientific. Examining the development and subsequent reception of this machine, I show that during the first decades of the 18th century these conceptions gave rise to a double image of this machine, and hence of agricultural knowledge in general: on the one hand, this machine was considered as more efficient and productive (while still in need of improvement); on the other hand, it was viewed, either implicitly or explicitly, as something that should be studied by mathematicians, thus reflecting a changing image of mathematics. [ABSTRACT FROM AUTHOR]

Global Navigation Satellite Systems-Interferometric Reflectometry (GNSS-IR) is an emerging remote sensing technique studied and demonstrated for soil moisture retrieval over bare soil using multipath GNSS data. However, retrieval of soil moisture in the presence of vegetation/crops is still a very challenging task even becoming a more complex problem without using any ancillary datasets to compensate the vegetation effect for soil moisture retrievals in higher crop growth stages. This paper presents a novel multipath phase-based vegetation correction scheme for improved field-scale soil moisture retrieval using L-band data from Navigation with Indian Constellations (NavIC) based on GNSS-IR technique. The proposed three steps vegetation correction scheme categorized the crop as per growth stages for sensitivity analysis of NavIC derived multipath phase as GNSS-IR observables and significantly compensated vegetation effects on multipath phase for improved soil moisture retrievals. The proposed method utilized only multipath phase data as single SNR metrics without any ancillary data sets and validated during complete growth cycle of winter wheat crop (sowing to harvesting stages). It has been shown that the soil moisture retrieved using proposed vegetation correction scheme provides a Pearson correlation coefficient of 0.87 and ubRMSD of 0.0341 m3/m3 with in situ measured soil moisture, which is better than bare scheme with Pearson correlation coefficient of 0.71 and ubRMSD of 0.0480 m3/m3. Overall, proposed scheme has found highly effective for vegetation correction and has shown a good potential candidate for VSM retrievals over crop-covered soil using other GNSS constellations (GPS, GLONASS, Galileo and BeiDou etc.). [ABSTRACT FROM AUTHOR]

This paper shows an agricultural irrigation alternative using a low-cost Internet of Things (IoT) application. This technology allows the automation and optimization of processes by monitoring, processing, and analyzing large volumes of related data, including variables related to the soil (moisture), fertilization, and irrigation, which can be visualized through the internet to enable sustainable and efficient agriculture. The study is centered on the Los Angeles, Biobío, Chile case. The main objective of the prototype is to optimize water consumption for agricultural irrigation by using only the amount that is strictly necessary for each crop by allowing real-time visualization of irrigation status, moisture data, and irrigation times while providing a history of data that can be used for further analysis. [ABSTRACT FROM AUTHOR]

Smart farming is a new concept that can be described as applying different kinds of modern technology to make farming more efficient. One such technology is the Internet of Things, an extension of the Internet and other connections into mundane devices. This paper uses dedicated sensors and cloud computing technologies to model a smart farming system that helps farmers keep track of state of the crops and livestock. It also covers implementing and testing an Android tracker app that is supposed to become the first component of the mentioned system, a client application that communicates with the cloud computing services yet to be implemented. The end product provides its users with an easy way of keeping track of the state of their farms, simplifying the farmers' work and enhancing productivity. [ABSTRACT FROM AUTHOR]

This paper contributes to the discussion on climate change impacts, livelihood diversification, and deagrarianization in arid and semi-arid regions. Using the semi-arid region of Guinea as a case study, this paper is the first to discuss the primary factors driving smallholder farmers into artisanal and small-scale mining (ASM) in arid and semi-arid regions. Drawing on in-depth interviews and root-cause analysis, we find that increasing climate change impacts 'force' smallholder farmers to switch into artisanal gold mining. Smallholder farming in semi-arid Guinea is largely rainfed and erratic rainfall and increasing temperatures have affected crop production and farmers' income, driving many smallholder farmers into artisanal gold mining to have a more sustainable income. While artisanal gold mining has improved smallholder farmers' socioeconomic conditions, the agriculture exodus has significantly affected crop production, food prices, and rural agriculture labor dynamics. Agroecological, financial, and technical support could improve the adaptive capacity of climate impacted smallholder farmers in arid and semi-arid regions. • Agrarian communities are now transforming into artisanal mining communities due primarily to climate change. • Dry farmlands, low farm productivity, and low farm income are secondary factors that drive farmers into the ASM economy. • Farmers converted to miners to cope with climate change impacts and not necessarily to 'get rich quick'. • Smallholder farmers in semi-arid Guinea lack access to climate adaptive strategies. • Livelihood diversification from farming to ASM affects rural socioeconomics and threatens food security. [ABSTRACT FROM AUTHOR]

The motivation of this paper stems from the growing concern of heavy pesticide use in developing countries such as Sri Lanka. Its excessive use affects the environment, the economy and farmers' health and yet farmers still seem unaware of its ill-effects. More worrying is the lack of appropriate government efforts to address this problem. If neglected, heavy use of pesticide eventually renders land useless, reduces future farm output and productivity and can severely affect farmers' health. This paper investigates pesticide use in agriculture and its impact on farm level technical efficiency using a metafrontier framework with stochastic frontier analysis. Data are collected through surveys of two groups of farmers in Sri Lanka. The first (described as the 'non-hospitalized farmers') are farmers who perceive that their ill-health is due to exposure to pesticides and obtained treatment but are not hospitalized. The second group (described as the 'hospitalized farmers') are farmers whose ill-health has been diagnosed by doctors and have been treated in hospital for exposure to pesticides. The results show that farmers overuse pesticides because of higher expectations of future returns which has led to an increase in inefficiency and remains unknown to the farmers. Determinants of inefficiency supports the argument that pesticide induced health problems reduce the health capital, while increasing farm level inefficiency. [ABSTRACT FROM AUTHOR]

Finding pathways to enhance the resilience of farming systems (FSs) in Europe is key, given the increasing challenges threatening them. FSs are complex socio-ecological systems in which social and ecological components are strongly linked. Social actors have the capacity to shape the FSs' resilience, but there is a knowledge gap about how they can best do it. The aim of this paper is to analyse the roles played by the actors in FSs when dealing with challenges and assess how these roles may contribute to the resilience attributes (conditions that enable resilience) and resilience capacities (robustness, adaptability, and transformability). To this end, ten focus groups have been conducted across FSs in Europe. Results suggest that each actor in the FSs can shape and strengthen different resilience attributes which in turn result in combinations of resilience capacities that are specific to the FS. Thus, enabling resilience is best accomplished with actors taking different roles and jointly configuring the most adequate combination of capacities, which differs across FSs. This paper provides a set of resilience-enabling roles that delineate the pathways to make FSs more resilient. The diversity of actors and resilience-enabling pathways require flexible, coordinated and comprehensive policies that encompass the complexity of the socio-ecological systems. • Enabling resilience of farming systems is best accomplished with actors taking different roles. • Improving farming systems' resilience requires enhancing their transformability capacity. • The actors enhance resilience by reinforcing human capital, response diversity, social organization and learning. • This paper provides a set of resilience-enabling roles that delineate the pathways to make farming systems more resilient. [ABSTRACT FROM AUTHOR]

Lameness is a significant health and welfare issue in farmed animals. This paper uses a governmentality approach, which focuses on how a problem is made governable, to examine an emerging 'ecology of devices' introduced to intervene in, and attempt to reduce, on-farm incidence of lameness. These devices are associated with advisers who work with farmers on-farm; they enact lameness as a governable entity, are tools to assess the existence of lameness against established norms, and prescribe actions to be taken in response to evidence of lameness. In doing this they subjectify farmers and advisers into seeing and responding to lameness in particular ways. Using concepts of governmentality alongside other perspectives on the power relations and the simplifications and complexities involved in interventions in animal health and farm practice, the paper draws on in-depth research with advisers including vets and other paraprofessionals who work with farmers, and their cows and sheep. It explores how this set of devices introduces particular techniques and practices in lameness management, and produces farmer and adviser subjectivities. It then explores some of the problematics of this mode of governing lameness, including analysis of the limitations and unintended consequences of attempts to simplify lameness management. The paper concludes by arguing that its approach is valuable in analysing ongoing intensification of interventions in farming practices and in understanding the limits of such interventions and the unanticipated divergences from expected conduct. • A governmentality approach to livestock lameness provides valuable insight into recent attempts to reduce its prevalence and severity on farms. • The government of lameness produces farmer and adviser subjectivities linked to new tools and devices aiming to reduce the incidence of lameness. • The government of lameness is limited by complexities linked with attempts to simplify interventions and deviation from expected practices. [ABSTRACT FROM AUTHOR]

At the heart of India's livelihood lies agriculture, a foundational and ever-evolving sector. The realm of agriculture faces modern challenges, encompassing unpredictable climate fluctuations, insufficient irrigation infrastructure, and erratic weather conditions. Amidst these challenges, machine learning has emerged as a valuable tool for evaluating soil fertility and Crop assessment in agriculture. Ensemble machine learning methodologies have garnered attention for their potential to enhance predictive capabilities. These techniques involve constructing meta-classifiers that collectively contribute to improved predictive accuracy. This paper centers on the analysis of soil data acquired from testing laboratories, to predict fertility based on a comprehensive dataset. The study employs prominent ensemble machine learning algorithms, specifically focusing on boosting techniques, to elevate predictive accuracy and ensure heightened consistency. The assessment of soil fertility categories involved the examination of 12 carefully chosen attributes. Diverse soil parameters were measured to facilitate the prediction of soil fertility levels. The outcomes of the experimentation revealed that the application of the boosting technique using the Xgboost algorithm yielded superior accuracy compared to alternative ensemble classifiers, achieving a remarkable 96% accuracy rate. [ABSTRACT FROM AUTHOR]

Techniques for classifying data using data mining are now a day prevalent in agriculture. The method of classifying seeds involves grouping various seed varieties according to their morphological characteristics. To accomplish categorization of the typical Charotar region (generally comprising Anand and Kheda districts of the Gujarat State of India) Gujarat Wheat (GW) varieties (TRITICUM – AESTIVUM) viz. GW 273, GW 496, GW 322, LOK-1, and GDW 1255 (TRITICUM – DURUM), Weka Explorer was used. The features used are area, perimeter, solidity, aspect ratio, major and minor axis of seed kernel, Hue, Saturation, Value, and SF1 (empirical). Features reduction was done using Information Gain (IG) and its modified version Gain Ratio (GR). This paper compares performance of Tree based data mining algorithms in classifying wheat varieties. For classification we used purely tree-based machine learning algorithms viz. J48, Random Forest, Hoeffding Tree, Logistic Model Tree (LMT), and REPTree. LMT- logistics regression method gives higher accuracy 96.4% compared to other classifiers. Hoeffding Tree classifiers stood second with 96% accuracy. For validation 10-fold cross validation was used. By reducing the number of folds in cross validation performance of most algorithms decreased except J48. The percentage of correctly classified instance increased for all algorithms when features were selected by GR except for J48. [ABSTRACT FROM AUTHOR]

The study of market power in the primary foods industry is of high interest to policymakers seeking to help develop low-income countries, due to its potential source to create market inefficiencies and hamper economic development. Recent studies have provided ample empirical evidence, that market power has been increasing nearly continuously since the 1980s. Nevertheless, due to the (un)availability of firm-level data, most research is constrained to analyzing firms within industries of a few high-income with a particular focus on manufacturing and service sectors. This paper proposes to remedy this gap in the literature by using aggregate data contained within the Eora Input-Output Tables and a procedure based on Generalized Maximum Entropy to provide estimates of the markup for the primary foods industry (defined as the agriculture, hunting, logging and fishing industries) for 43 countries in Asia. We document a large heterogeneity based on a country's income level classification. Furthermore, measures of globalization are seen to significantly reduce markups. Opening up to trade might therefore be an attractive option to policymakers seeking to stimulate economic efficiency. [ABSTRACT FROM AUTHOR]

Since the implementation of herding in the Neolithic period, specialized areas for livestock activities have emerged in the Western Mediterranean region, such as some caves and shelters, which were systematically used for the stabling of herds. By definition, this type of sites has a great potential for the study of the beginning of livestock practices and offer high-resolution information on the exploitation and management of herds. Different disciplines analyze these activities through the analysis of faunal, archaeobotanical or sedimentological remains from these sites. In this paper, we offer a state of the art on the contribution to the study of early husbandry practices of zooarchaeological studies of faunal assemblages from sheepfold caves. [ABSTRACT FROM AUTHOR]

• Seriphium plumosum L. is a taxonomically recalcitrant complex of paper daisies distributed in southern Africa. • The complex has been shown to comprise at least seven independent species. • Stoebe burchellii Levyns, Stoebe virgata Thunb. and Stoebe vulgaris Levyns are reinstated in Seriphium. • Four species new to science are described in Seriphium. • Seriphium vulgaris (Levyns) Z.Shaik is the only species in the S. plumosum complex that is an agricultural weed on millions of hectares of South African rangeland. Seriphium plumosum L. from southern Africa has been shown to comprise at least seven distinct species based on analysis of morphological, environmental, and multilocus DNA sequence data. On that evidence, Stoebe burchellii Levyns, Stoebe virgata Thunb., and Stoebe vulgaris Levyns are reinstated in Seriphium , and four new species are described, viz., Seriphium alto-argillaceum Z.Shaik , Se. burrowsii Z.Shaik , Se. crypticum Z.Shaik , and Se. dunensis Z.Shaik. Four of these species are endemic to the Cape Floristic Region of South Africa, and one is so far known from a single high-elevation locality. We present a key to species in the Seriphium plumosum complex, and for each species provide a formal description with accompanying images, typification and synonymy, with distribution maps based on verified field-collected and herbarium specimens. [ABSTRACT FROM AUTHOR]

The remarkable performance of Convolutional Neural Networks (CNNs) has increased their use in real-time systems and devices with limited resources. Hence, compacting these networks while preserving accuracy has become necessary, leading to multiple compression methods. However, the majority require intensive iterative procedures and do not delve into the influence of the used data. To overcome these issues, this paper presents several contributions, framed in the context of e x plainable Artificial Intelligence (xAI): (a) two filter pruning methods for CNNs, which remove the less significant convolutional kernels; (b) a fine-tuning strategy to recover generalization; (c) a layer pruning approach for U-Net; and (d) an explanation of the relationship between performance and the used data. Filter and feature maps information are used in the pruning process: Principal Component Analysis (PCA) is combined with a next-convolution influence-metric, while the latter and the mean standard deviation are used in an importance score distribution-based method. The developed strategies are generic, and therefore applicable to different models. Experiments demonstrating their effectiveness are conducted over distinct CNNs and datasets, focusing mainly on semantic segmentation (using U-Net, DeepLabv3+, SegNet, and VGG-16 as highly representative models). Pruned U-Net on agricultural benchmarks achieves 98.7% parameters and 97.5% FLOPs drop, with a 0.35% gain in accuracy. DeepLabv3+ and SegNet on CamVid reach 46.5% and 72.4% parameters reduction and a 51.9% and 83.6% FLOPs drop respectively, with almost no decrease in accuracy. VGG-16 on CIFAR-10 obtains up to 86.5% parameter and 82.2% FLOPs decrease with a 0.78% accuracy gain. • New filter pruning and fine-tuning strategies for segmentation and classification. • Novel layer pruning method for U-Net, a relevant semantic segmentation model. • Performing a detailed pruning survey on encoder–decoder and classification models. • Significant reduction in parameters and FLOPs maintaining networks efficiency. • Analyzing the dependence of the pruned models performance on the used dataset. [ABSTRACT FROM AUTHOR]

Despite the remarkable progress of deep learning-based object extraction in revealing the number and boundary location of geo-objects for high-resolution satellite imagery, it still faces challenges in accurately extracting blurry dense objects. Unlike general objects, blurry dense objects have limited spatial resolution, leading to inaccurate and connected boundaries. Even with the improved spatial resolution and recent boundary refinement methods for general object extraction, connected boundaries may remain undetected in blurry dense object extraction if the gap between object boundaries is less than the spatial resolution. This paper proposes a blurry dense object extraction method named the buffer parsing network (BPNet) for satellite imagery. To solve the connected boundary problem, a buffer parsing module is designed for dense boundary separation. Its essential component is a buffer parsing architecture that comprises a boundary buffer generator and an interior/boundary parsing step. This architecture is instantiated as a dual-task mutual learning head that co-learns the mutual information between the interior and boundary buffer, which estimates the dependence between the dual-task outputs. Specifically, the boundary buffer head generates a buffer region that overlaps with the interior, enabling the architecture to learn the dual-task bias and assign a reliable semantic in the overlapping region through high-confidence voting. To alleviate the inaccurate boundary location problem, BPNet incorporates a high-frequency refinement module for blurry boundary refinement. This module includes a high-frequency enhancement unit to enhance high-frequency signals at the blurry boundaries and a cascade buffer parsing refinement unit that integrates the buffer parsing architecture coarse-to-fine to recover the boundary details progressively. The proposed BPNet framework is validated on two representative blurry dense object datasets for small vehicle and agricultural greenhouse object extraction. The results indicate the superior performance of the BPNet framework, achieving 25.25% and 73.51% in contrast to the state-of-the-art PointRend method, which scored 21.92% and 63.95% in the A P 50 s e g m metric on two datasets, respectively. Furthermore, the ablation analysis of the super-resolution and building extraction methods demonstrates the significance of high-quality boundary details for subsequent practical applications, such as building vectorization. The code is available at: https://github.com/Dingyuan-Chen/BPNet. [ABSTRACT FROM AUTHOR]

As a result of the industry's inability to meet societal demand, Industry 4.0 was launched in the last decade years. To close the gap, the academic and industrial sectors are pursuing revolution. One strategy for moving forward is digital transformation, and the digital twin is the technology that best exemplifies this strategy by upending conventional industrial processes and functions. This paper will help audiences who lack expert knowledge of digital twins to swiftly evaluate and comprehend research advancements in academia and industry. It will cover the background, features, and implementation of the digital twin in five main sectors. The case study used in this paper is Qinghai Meadow in China, which uses the intended network to explain how digital twins have developed in the husbandry sector. At the end of the study, issues are also illustrated from two perspectives that aid in identifying gaps in the subject. [ABSTRACT FROM AUTHOR]

Abstract: Coastal fisheries, including industrial, artisanal and subsistence sectors, are an integral and vital part of the economies of south-east Asia with annual landings of >16 million tonnes. Most of these fisheries are either fully exploited or over-exploited and only meaningful and coordinated management of harvesting can hope to avert major collapses. Recognising the importance of an integrated and collaborative approach to research and management between countries sharing a common resource, the Worldfish Center organized an “International Workshop on Management of Tropical Coastal Fisheries in Asia” in March 2001. Five key papers from this workshop were selected for inclusion in this special section of Fisheries Research. [Copyright &y& Elsevier]

Current conventional agricultural practices have exacerbated the depletion of soil, loss of biodiversity, and intensified the substantial challenges of food security including monoculture dependence, resource intensiveness, access and distribution issues. This has raised consumers awareness towards monitoring the resources of their food consumption. Nevertheless, greenwashing and deceptive food labels are prevalent leading to sales of items with misaligned labels, underpinning the need to authenticate, trace, and track the agricultural supply chain from the farm to shop. Consumers should be able to select fresh produce and verify its origin through a transparent, trustworthy, accountable, and reliable process. This paper introduces a blockchain-based solution that leverages intrinsic features of this innovative and disruptive technology to harness transparency, reliability, authenticity, and accountability within an agricultural supply chain. Additionally, our solution eliminates misleading food labels on fresh produce by enabling consumers to reliably trace and verify the origin and authenticity of the food source in a transparent manner. Through the integration of the Internet of Things (IoT), the well-being of the soil, air, and crops is consistently monitored. The sustainable solutions employed are transparent, aligning with the standards set by various sustainable food certifications and agencies, including organic, non-Genetically Modified Organisms (GMO), and Good Agricultural Practices (GAP). The paper presents detailed algorithms that represent the smart contract code, sequence diagrams along with testing results and security analysis. The smart contract code is made publicly available on GitHub. • Integration of Blockchain, IoT, & biosensors to ensure eco-friendly crop monitoring. • Ensures transparent, traceable food certification and fosters trust. • Effective anomaly handling and clear, accountable food certification. • Solution aligns with agencies (organic, non-GMO, GAP), adaptable to needs. [ABSTRACT FROM AUTHOR]

Precise detection and effective intervention of pathogenic microorganisms are pivotal to ensure crop yield. Traditional open set recognition methods distinguish unknown classes, i.e., those not involved in training, as outliers or separate classes, which is insufficient for real-world applications like recognizing airborne microorganisms and particles. In this paper, a new setting for the classification of outliers for open set recognition is proposed. The proposed method classifies unknown classes while achieving the classification of known classes, treating each category in the open set equally. The two cores of the method are hierarchical feature representation and feature gallery construction. To enhance the feature representation, this paper proposes a novel architectural module of spatial attention on region hierarchy, namely SPARC. This module extracts features from hierarchical levels and models spatial interaction through the attention mechanism. With the induction of local-to-global description, minute differences with ambiguous appearances between classes can be detected, and the negative effects of image quality degradation can be ameliorated. Furthermore, a feature gallery containing the feature representation from both known and unknown classes is developed for feature retrieval. To demonstrate the effectiveness of the proposed model, the first dataset composed of agricultural microorganisms, named SMAD, is constructed, and experiments are conducted on existing datasets and the newly proposed SMAD dataset. The experimental results outperform the prior art on these datasets under both the outlier rejection and outlier classification settings. • SMAD is the first dataset in the field of agricultural microorganisms. • We propose an OSR framework based on feature representation and feature retrieval. • The proposed framework can categorize known and unknown pathogenic fungal spores. • Our method outperforms existing approaches and stands out in outlier classification. [ABSTRACT FROM AUTHOR]

Emerging contaminants (ECs) are gaining attention due to their prevalence and potential negative impacts on the environment and human health. This paper provides a comprehensive review of the status and trends of soil pollution caused by ECs, focusing on their sources, migration pathways, and environmental implications. Significant ECs, including plastics, synthetic polymers, pharmaceuticals, personal care products, plasticizers, and flame retardants, are identified due to their widespread use and toxicity. Their presence in soil is attributed to agricultural activities, urban waste, and wastewater irrigation. The review explores both horizontal and vertical migration pathways, with factors such as soil type, organic matter content, and moisture levels influencing their distribution. Understanding the behavior of ECs in soil is critical to mitigating their long-term risks and developing effective soil remediation strategies. The paper also examines the advantages and disadvantages of in situ and ex situ treatment approaches for ECs, highlighting optimal physical, chemical, and biological treatment conditions. These findings provide a fundamental basis for addressing the challenges and governance of soil pollution induced by ECs. [Display omitted] • The research status of ECs on soil have been reviewed. • A possible interaction mechanism between soil and ECs has been proposed. • The distribution and migration pathways of ECs in soil have been described. • Promising future directions have been proposed for mitigating the contamination of soil by ECs. [ABSTRACT FROM AUTHOR]

Ideally, scientific results are communicated such that they can be critically assessed, discussed, and used for future research by the scientific community. Replication studies that test and also verify earlier results ensure trust in the scientific work and discussion culture. In this note, we illustrate main challenges in replication studies using the example of a recently published replication attempt of a paper entitled 'Terrorism and land use in agriculture: The case of Boko Haram in Nigeria' on the effects of armed conflict on agricultural land use and the corresponding reaction of the authors of the initial research paper. We argue that a comprehensive, transparent description of the data and methods used is just as crucial as the opportunity to objectively, constructively, and fairly discuss criticism during the replication process. From this series of articles, we further derive lessons for replication debates in general by highlighting challenges and possible ways of dealing with strained relations between authors and replicators. Rethinking solutions to ensure supportive collaborations is crucial in shaping the future discourse surrounding replication debates. • Replication studies test and verify earlier results to ensure trust in the scientific work and discussion culture. • A comprehensive, transparent description of the data and methods used is necessary. • The opportunity to objectively, constructively, and fairly discuss criticism during the replication process is crucial. • We highlight challenges in replication debates and suggest ways to avoid strained relations between authors and replicators. [ABSTRACT FROM AUTHOR]

The growing integration of AI in agriculture necessitates access to diverse data sets for training artificial intelligence (AI) systems. Manufacturers often face challenges due to a perceived shortage of valid data sets, highlighting the need for centralized platforms offering high-quality data. While global AI regulations are yet to be established, existing laws govern data collection, creation, labeling, and processing for AI training in various legal systems. The absence of explicit AI laws prompts a call for platforms supplying data to adhere to relevant regulations, especially in areas where AI controls devices interacting with humans, such as collision warning systems in yard tractors and robots. Compliance is crucial, given the complexity of rules governing data sets featuring people, animals, and buildings. The paper focuses on how to check the compliant data sets in Germany's legal context, focusing on situations in farm yards. People are often visible on such data sets; thus, the data set must preserve the right to informational self-determination and one's image, which is prevalent in many legal systems. Images portraying people typically qualify as personal data, requiring careful anonymization to address privacy concerns. The paper uses artificial neural networks (ANN) to remove images that contradict people's rights on one's image; thus, data sets that comply with data protection laws can be created. It also addresses the lesser-explored issue of the right to one's image in German law. Though AI training may not be impeded, dissemination via digital platforms must adhere to legal boundaries, even if metadata is absent. The paper suggests an AI solution to identify images within legal limits, detect violations, and modify them to create a legally compliant data set respecting the right to one's image. • Discussing legal conform data sets for the agricultural application domain. • Providing a data set of 2694 images covering the categories: – class (I) not legally compliant and – class (II) legally compliant on the right to one's image; cf. Fig. 1. • Identifying the gap in ANN data sets and models for law compliance checks. • Train and benchmark ANN models for checking law compliance – on the right to one's image; – cf. Tab. 1, Tab. 2, and Fig. 3. • Promoting the importance of AI-based law compliance checks for – detecting violations against the law and – developing compliant AI systems in agriculture. [ABSTRACT FROM AUTHOR]

As interest grows in facilitating, funding, and investigating inclusive innovation processes in agrifood systems in the Global South, a need has emerged for middle-range theory that can describe the key features and causal dynamics of these processes across diverse contexts. This paper advances theory-building by testing and refining an existing middle-range theory of inclusive innovation processes in agrifood systems in the Global South through a case study of an inclusive innovation process involving smallholder farming communities in the Ecuadorian Andes. We used a case study replication design to test the initial theory. To develop the case study, we conducted primary qualitative research, including interviews, informal personal communications, and document reviews. Data analysis was conducted in two phases: in the first phase, we developed a timeline and causal narrative of the case and in the second phase, we conducted inductive and deductive thematic analysis. We find that each component of the existing middle-range model played an important role, as predicted, in the inclusive innovation process described in the case study. Our analysis also reveals additional component categories, including process inputs, initial contextual conditions, and actor-level mechanisms, that featured prominently in the case but were omitted from the existing theory. The case also revealed a more nuanced, phased causal dynamic than that described in the existing middle-range model and identified intermediate pilot results as boundary objects that expanded the inclusivity of the innovation process and triggered the causal dynamics predicted by the existing theory. Our findings inform a revision to the existing mid-level model, contributing to building an empirically validated theory of how inclusive innovation processes unfold in agrifood systems that sheds light on specific features of these processes that are important for promoting inclusivity. [Display omitted] • Theoretical models of inclusive innovation processes in agrifood systems are in early stages of development. • This paper tests and refines an existing model through a case study of a sucessful inclusive innovation process. • The revised model contains components and a phased causality that more accurately reflect the dynamics of the case. • New components include inputs, initial contextual factors, actor-level causal mechanisms, and early results. • Pilot results serve as boundary objects that trigger motivation to engage among a wider and more diverse set of actors. [ABSTRACT FROM AUTHOR]

Worldwide greenhouse gas emissions (GHG) reached 59 Gt of CO 2 eq in 2019 and agricultural soils are the primary source of N 2 O emissions. Life cycle assessments (LCA) have been successful in assessing GHG from agricultural systems. However, no review and harmonization attempt has been focused on soil N 2 O emissions, despite the need to improve LCA methodologies for assessing GHG in agricultural LCA. We therefore undertook a review and harmonization of existing methods to account for soil N 2 O emissions in LCA of agricultural systems and products: i) to compare current methods used in LCA; ii) to identify advantages and iii) disadvantages of each method in LCA; iv) to suggest recommendations for LCA of agricultural systems; v) to identify research needs and potential methodological developments to account for soil N 2 O emissions in the LCA of agricultural systems. In this paper, we consider as soil N 2 O emissions, those originated from soils in relation to fertilisers (organic and manufactured), crop residues, land use/land management change, grassland management, manure and slurry applications and from grazing animals. The approach adopted was based on two anonymous expert surveys and a series of expert workshops (n = 21) to define general and specific criteria to review LCA methods for GHG emissions used in LCA of agricultural systems. A broad list of keywords and search criteria was used as the research involved GHG assessment in agricultural LCA. Reviewed papers and methodology were then assessed by LCA and soil N 2 O emission experts (n = 14). >25,000 scientific papers and reports were identified, 1175 were screened, 263 included in the final review and 31 scientific papers were related to soil N 2 O emissions. The results showed that a high level of accuracy corresponded to a low level of applicability and vice versa, following the assessment framework developed in this work through participatory approaches. The choice of LCA methods, critical for high quality LCA of agricultural systems, should be based on the assessment objectives, data availability and expertise of the LCA practitioner. However, it is preferable to use DNDC model after calibration and validation or direct field measurements, considering system effects. When necessary data are lacking, IPCC tier 2 methodology where available should be used, otherwise 2019 IPCC Tier 1 methodology. This LCA method development should be synchronous with improvements of quantification methods and the assessment of a wider range of agricultural management practices and systems. [Display omitted] • Methods used in life cycle assessment (LCA) of agricultural systems to account for soil N 2 O need to be improved. • A method harmonization was carried out and recommendations for soil N 2 O emissions were identified in agricultural LCA. • The results showed that a high level of accuracy corresponded to a low level of applicability and vice versa. • DNDC, DAYCENT and direct measurements scores high on accuracy to assess soil N 2 O emissions in LCA of agricultural systems. • Alternative to DNDC and measurements are IPCC Tier 1 or 2 methodologies to assess soil N 2 O emissions in agricultural LCA. [ABSTRACT FROM AUTHOR]

Amid the swift evolution of advanced technologies such as autonomous robotics, edge computing, and the Internet of Things, Intelligent Agriculture Management Systems (IAMS) have become increasingly pivotal in contemporary smart agriculture. One vital task, crop disease monitoring, significantly contributes to ensuring agricultural production quality and food supply security. However, IAMS encounters a particular challenge: due to the limited computational capacity of agricultural equipment and the scarcity of available training datasets, general detection models struggle to achieve anticipated performance in agricultural environments, especially when dealing with small-scaled targets. In this paper, we propose a diffusion learning detector named CropDetdiff, designed for disease detection in agricultural environments where training samples are limited. We have developed a backbone network based on dynamic convolutional kernels, which also embeds a graph attention network in its final stage, enhancing feature extraction capabilities for small targets. Additionally, we employ a fuzzy label assignment strategy to balance positive and negative samples and devise a new loss function, HIoU, to supervise the detection of small targets. A series of experiments on two crop disease datasets validate that CropDetDiff achieves an optimal balance between detection performance and operational efficiency. Specifically, the proposed model has achieved a mean Average Precision (mAP) of 73.2% and 40.1% on the two datasets, improving by at least 3.7% and 2.9% over other detectors, respectively, and there is a significant improvement in small targets particularly, thus achieving optimal performance. Additionally, the proposed model exhibits commendable performance in terms of parameter quantity and execution velocity. These results substantiate the efficacy and stability of CropDetDiff, underscoring its suitability for real-world applications within IAMS. • This paper builds the graph-embedded lightweight backbone network with learnable convolutional kernels (LCSPNet) to mine small targets and their potential graph connections with the background, so that the model can better cope with the detection of multi-scale features under crop dense distribution, especially small targets. • One-to few label assignment strategy is proposed to optimize the imbalance of positive and negative samples in the training process, and add it to the detection head to detect the target region more accurately. Furthermore, we use the new detection head to achieve efficient redundant box suppression in the diffusion learning process of the detection frame. • This study used two small crop diseases datasets to validate the model. Abundant experiments prove that the proposed model achieves good performance results, which can be better adapted to practical applications in different scenarios. [ABSTRACT FROM AUTHOR]

Fruits and vegetables are major sources of nutrients for the majority of the population across the globe. With the rapid increase in population, the objectives of the future agro-industry are to reduce product loss while increasing product quality and productivity considerably. Consequently, farmers need to be assisted with cutting-edge technologies for sustainable, eco-friendly, and efficient farming. Smart farming for early disease recognition and control is the current hot-spot research objective in the fruitage domain. The precision agriculture era has been revolutionized by federating cutting-edge technologies like machine learning, deep learning, and, the Internet-of-Things. However, the existing studies focused on the impact of individual technology on single or multiple cultivars of edible fruits or vegetables. Limited areas of the fruitage disease remain explored, necessitating further investigation into the research gaps and challenges identified for implementing the smart practices in real-field farmlands. In this paper, a comprehensive survey of recent advancements in fruit and vegetable disease identification and classification is presented. The technology-wise state-of-the-art findings, gaps, challenges, and future opportunities for fruitage disease recognition have been presented, covering 99 research articles. Moreover, the corpus of publicly available fruit and vegetable datasets has been investigated, with the existing gaps, improvements, and future requirements. The research paper concludes with challenges and a future outlook that promises to be a very significant and valuable resource for researchers working in the area of agronomic disease monitoring. [ABSTRACT FROM AUTHOR]

• Proposed FSDnet has good performance in crop plant phenotype segmentation. • Introduced Gaussian density can reduce the calculation and improve accuracy. • By embedding FSDnet, the traditional models can work well in different densities. • We construction a new field 3D deep learning dataset including strawberry and apple. The accurate segmentation of fruit phenotypes in the field is of great significance for agricultural automation in the 3D scene. Although the existing fruit segmentation based on 3D point cloud has made great progress, in the complex field environment, due to lighting, leaf occlusion, shooting angle and other problems, the point cloud obtained by depth camera often has the problem of multiple voids and discrete points, which seriously affects the accurate segmentation of fruit phenotype. This paper proposes a embedding subnetwork FSDnet based on density-based feature extraction and feature propagation and embeds it in the novel segmentation networks, which effectively improves the segmentation accuracy of the point cloud phenotype in multi-hole and multi-discrete fruits, including (1) The density-based point cloud feature extraction and feature propagation theory is proposed to alleviate the problem of perception degradation in fruit edge point caused by discrete points and holes caused by imcomplete point cloud in the agriculture scene. (2) A density-adaptive embedding semantic segmentation framework FSDnet is proposed, and embedding the classical point cloud neural network can significantly improve the segmentation accuracy of the fruit phenotypes with multiple holes and discrete points in the traditional network. (3) This paper made a strawberry dataset and tested the designed new neural network on both strawberry and apple filed dataset. After FSDnet is embedded on different novel net, almost all net have been improved. We verified the performance of FSDnet in different density states in agricultural scenarios, mitigated the negative impact of density on segmentation accuracy, proving that it can adapt to different point cloud density in agricultural scenarios in comparison between Gaussian density and other two traditional density schemes, Gaussian density reduces the computational traffic (0.58G) of the network while maintaining similar performance to the other two densities, proving the superiority of assuming a Gaussian density. [ABSTRACT FROM AUTHOR]

Current technology has made it possible to automate a number of agricultural processes that were traditionally carried out by humans and now can be entirely performed by robotic platforms. However, there are certain tasks like soft fruit harvesting, where human skills are still required. In this case, the robot's job is to cooperate/collaborate with human workers to alleviate their physical workload and improve harvesting efficiency. To accomplish that in a safe and reliable way, the robot should incorporate a safety system whose main goal is to reduce the risk of harming human co-workers during close human–robot interaction (HRI). In this context, this paper presents a theoretical study, addressing the safety risks of using collaborative robots in agricultural scenarios, especially in HRI situations when the robot's safety system is not completely reliable and a component may fail. The agricultural scenarios discussed in this paper include automatic harvesting, logistics operations, crop monitoring, and plant treatment using UV-C light. A human injury assessment is conducted based on converting the HRI in each agricultural scenario into a formal mathematical representation. This representation is later implemented in a probabilistic model-checking tool. We then use this tool to perform a sensitivity analysis that allows us to determine the probability that a human may get injured according to the occurrence of failures in the robot's safety or perception systems. Results of the sensitivity analysis show that an agricultural robot with a robust human perception system can still harm people if they are not well-trained to interact with the robot for certain scenarios. This illustrates how the probabilistic modeling methodology presented in this work can be used by safety engineers as a guideline to construct their own HRI models and then use the results of the model-checking to enhance the safety and reliability of their robot's safety system architectures and on-site safety policies. • Templates for hazard analysis and mitigation strategies in cooperative agricultural robotics. • Human–robot interactions in agricultural scenarios can be represented as simplified probabilistic models. • The reliability of robot safety systems/policies can be tested by formal verification before real implementation. • An agricultural robot with a robust human perception system can still harm people if they are not well-trained. • Ensuring that only trained people interact with agricultural robots, minimizes chances of producing human injuries. [ABSTRACT FROM AUTHOR]

In sub-Saharan Africa, agricultural intensification and urbanization have increased the risk of proliferation of rodents in rural and urban habitats. Management of rodent populations is a challenge in terms of food security and public health. However, conventional efforts to manage rodents are currently reactive and based on the inadequate use of synthetic chemical rodenticides, including first- and second-generation anticoagulants and acute rodenticides. This approach carries substantial environmental and health risks and has yielded limited success in terms of reduction of rodent populations sustainably. In this paper, which is the second part of a diptych, we advocate for a shift towards more sustainable and environmentally friendly approaches, such as Ecologically-Based Rodent Management (EBRM), as a realistic alternative to synthetic rodenticides. This method is based on a good knowledge of habitat use, species diversity and population dynamics of major rodent pests, and involves community-based interventions aimed at reducing rodent abundance to economically and hygienically acceptable levels in the long term. We present for the first time a comprehensive compilation of published and unpublished information derived from observational field studies conducted in Ethiopia, Niger, Nigeria, Benin, Mali, Mauritania and Senegal with the aim to provide an overview of EBRM case studies in these countries of sub-Saharan Africa. This paper intends to serve as a catalyst for change, encouraging the transformation of rodent management practices towards sustainable methods. We aim at stimulating further research and interventions that promote EBRM in Africa, ultimately fostering more environmentally conscious and effective solutions. [Display omitted] • In Africa, agricultural intensification and urbanization are major changes. • These changes increase the risk of rodent proliferation in rural and urban habitats. • Conventional rodent control relies on reactive, inappropriate use of rodenticides. • Ecologically-Based Rodent Management has been poorly tested in sub-Saharan Africa. • This method can be a realistic, sustainable and environment-friendly alternative. [ABSTRACT FROM AUTHOR]

Introduction: Encouraging safe work practices (SWPs) is challenging in agriculture. Group-based social learning has effectively promoted SWPs and health behaviors in other occupations, and could be applied in agriculture (e.g., through farmer discussion groups (DGs)). In Ireland, dairy DG members are more likely to adopt novel technologies and practices, a relationship that might extend to SWPs. The extent of SWP adoption among Irish dairy farmers is unknown. This paper evaluates a 2018 baseline study of SWP implementation, conducted as part of a dairy DG-based intervention study. Method: A paper-based survey of SWP implementation and safety self-perception was distributed to 1,220 farmers from 84 dairy DGs. For eight SWPs, associated with high-risk farm hazards (livestock, slurry, machinery, or tractors), farmers were asked how frequently they implemented these practices in the previous year, and how frequently they intended to do so next year (0: never, 1: rarely, 2: sometimes, 3: most of the time, 4: all of the time). Results: Surveys were completed by 460 farmers. For the previous year, three SWPs, related to slurry, machinery, and tractor hazards, scored a median frequency of four. Four SWPs, related to livestock, slurry, and machinery hazards, scored a median frequency of three. The lowest median score (two) was for tractor exit behavior. Median intention scores matched or exceeded past frequency for all SWPs, while 73% intended to increase implementation of at least one SWP. Most (96%) considered themselves a "safe farmer." Conclusions: Farmers generally perceived themselves to be safe at work, which is reflected in their SWP implementation. Most farmers intended to increase SWP implementation, suggesting awareness of safety shortcomings and a desire to farm more safely. Practical applications: This study can inform farm safety promotion initiatives. The disconnect between farmers' safety self-perception and SWP implementation merits further research. [ABSTRACT FROM AUTHOR]

This paper discusses how the theory of affordances can be used to investigate how a spectrum of opportunities, benefits, costs and risks is generated and unevenly distributed by different kinds of technology (where 'technology' is understood as techniques, processes and practices of doing and making, rather than technical artefacts and systems). Affordances are possibilities for action, which arise from relations between humans and entities that surround them. This paper discusses three kinds of affordances: material, cultural and socio-economic. The theory of affordances offers a coherent way to explain why different technologies have different implications, and why those implications vary for different stakeholders. Applied to the domain of development-oriented agricultural research and innovation, the theory of affordances could be used by researchers and practitioners to examine the differentiated implications of different kinds of farming technology and alternative programmes of technological change in agriculture, both ex ante (e.g. in their design, development and implementation) and ex post (e.g. in their evaluation). To illustrate the argument, the paper uses the example of weeding in the System of Rice Intensification. Since affordances in theory are generated relationally and situationally for each person, the full array of implications arising from the introduction of new technology could be wide and diverse. A practical challenge, therefore, is whether and how the theory of affordances can be used practically and operationally to design, implement and evaluate the appropriateness, accessibility, utility and value of agricultural technology and technological change for specific people and groups of interest. • The theory of affordances is applied to agricultural technology and innovation. • Affordances are perceived action possibilities, which arise relationally. • Affordances can be studied through material, cultural and socio-economic lenses. • The theory of affordances could be applied to development interventions ex ante and ex post. • Weeding in the System of Rice Intensification is used to illustrate the argument. [ABSTRACT FROM AUTHOR]

The purpose of this paper is to address the hypotheses of complete urbanization and the post urban world with an emphasis on the agricultural sector. The paper studies spatial and temporal changes in land-use and agricultural activities in one rapidly growing metropolitan region, the Stockholm region. We explore the number and size of agricultural firms, changes in their main activity and trends of diversification and land prices for various types of land and location, all in a disaggregated spatial dimension. The results contribute to a deeper understanding of agriculture's function in metropolitan regions and shed new light on the possibilities of the agricultural sector to transform in a world where the traditional urban-rural relations are ceasing to exist. • Current spatial and temporal trends are put in an urban agricultural and land-use context of the post-urban world. • A striking decline in land use devoted to agriculture is found around the larger cities and the capital region. • Land prices are influenced by non-agricultural factors linked to urbanization, particularly the price of pasture. • Small and diversified farms have expanded most notably in areas nearby and surrounding the big cities. • Development trends can be linked to changing urban demand and increasing land prices [ABSTRACT FROM AUTHOR]