Experimental citizen science offers new ways to organize on-farm testing of crop varieties and other agronomic options. Its implementation at scale requires software that streamlines the process of experimental design, data collection and analysis, so that different organizations can support trials. This article considers ClimMob software developed to facilitate implementing experimental citizen science in agriculture. We describe the software design process, including our initial design choices, the architecture and functionality of ClimMob, and the methodology used for incorporating user feedback. Initial design choices were guided by the need to shape a workflow that is feasible for farmers and relevant for farmers, breeders and other decision-makers. Workflow and software concepts were developed concurrently. The resulting approach supported by ClimMob is triadic comparisons of technology options (tricot), which allows farmers to make simple comparisons between crop varieties or other agricultural technologies tested on farms. The software was built using Component-Based Software Engineering (CBSE), to allow for a flexible, modular design of software that is easy to maintain. Source is open-source and built on existing components that generally have a broad user community, to ensure their continuity in the future. Key components include Open Data Kit, ODK Tools, PyUtilib Component Architecture. The design of experiments and data analysis is done through R packages, which are all available on CRAN. Constant user feedback and short communication lines between the development teams and users was crucial in the development process. Development will continue to further improve user experience, expand data collection methods and media channels, ensure integration with other systems, and to further improve the support for data-driven decision-making.

While many have extolled the potential impacts of digital advisory services for smallholder agriculture, the evidence for sustained uptake of such tools remains limited. This paper utilizes a survey of tool developers and researchers, as well as a systematic -analysis of prior studies, to assess the extent and challenges of scaling decision support tools for site-specific soil nutrient management (SSNM-DST) across smallholder farming systems, where "scaling" is defined as a significant increase in tool usage beyond pilot levels. Our evaluation draws on relevant literature, expert opinion and apps available in different repositories. Despite their acclaimed yield benefits, we find that SSNM-DST have struggled to reach scale over the last few decades and, with strong heterogeneity in adoption among intended stakeholders and tools. For example, the log odds of a SSNM-DST reaching 5-10 % of the target farmers compared with reaching none, decreases by ∼200% when a technical problem is stated as a reason for the tools' failure to be used at scale. We find a similar decrease in odds ratios when technical, socioeconomic, policy, and R&D constraints were identified as barriers to scaling by national extension and private systems. Meta-regression analysis indicates that the response ratio of using SSNM-DST over Farmer Fertilizer Practice (FFP) varies by non-tool related covariates, such as initial crop yield potential under FFP, current and past crop types, acidity class of the soil, temperature and rainfall regimes, and the amount of input under FFP. In general, the SSNM-DST have moved one step forward compared with the traditional 'blanket' fertilizer recommendation by accounting for in-field heterogeneities in soil and crop characteristics, while remaining undifferentiated in terms of demographic and socioeconomic heterogeneities among users, which potentially constrains adoption at scale. The SSNM-DSTs possess reasonable applicability and can be labeled 'ready' from purely scientific viewpoints, although their readiness for system-level uptake at scale remains limited, especially where socio-technical and institutional constraints are prevalent.

The distribution of agricultural and livestock products has been limited owing to the recent rapid population growth and the COVID-19 pandemic; this has led to an increase in the demand for food security. The livestock industry is interested in increasing the growth performance of livestock that has resulted in the need for a mechanical ventilation system that can create a comfortable indoor environment. In this study, the applicability of demand-controlled ventilation (DCV) to energy-efficient mechanical ventilation control in a pigsty was analyzed. To this end, an indoor temperature and CO concentration prediction model was developed, and the indoor environment and energy consumption behavior based on the application of DCV control were analyzed. As a result, when DCV control was applied, the energy consumption was smaller than that of the existing control method; however, when it was controlled in an hourly time step, the increase in indoor temperature was large, and several sections exceeded the maximum temperature. In addition, when it was controlled in 15-min time steps, the increase in indoor temperature and energy consumption decreased; however, it was not energy efficient on days with high-outdoor temperature and pig heat.

Collection of accurate and representative data from agricultural fields is required for efficient crop management. Since growers have limited available resources, there is a need for advanced methods to select representative points within a field in order to best satisfy sampling or sensing objectives. The main purpose of this work was to develop a data-driven method for selecting locations across an agricultural field given observations of some covariates at every point in the field. These chosen locations should be representative of the distribution of the covariates in the entire population and represent the spatial variability in the field. They can then be used to sample an unknown target feature whose sampling is expensive and cannot be realistically done at the population scale. An algorithm for determining these optimal sampling locations, namely the multifunctional matching (MFM) criterion, was based on matching of moments (functionals) between sample and population. The selected functionals in this study were standard deviation, mean, and Kendall's tau. An additional algorithm defined the minimal number of observations that could represent the population according to a desired level of accuracy. The MFM was applied to datasets from two agricultural plots: a vineyard and a peach orchard. The data from the plots included measured values of slope, topographic wetness index, normalized difference vegetation index, and apparent soil electrical conductivity. The MFM algorithm selected the number of sampling points according to a representation accuracy of 90% and determined the optimal location of these points. The algorithm was validated against values of vine or tree water status measured as crop water stress index (CWSI). Algorithm performance was then compared to two other sampling methods: the conditioned Latin hypercube sampling (cLHS) model and a uniform random sample with spatial constraints. Comparison among sampling methods was based on measures of similarity between the target variable population distribution and the distribution of the selected sample. MFM represented CWSI distribution better than the cLHS and the uniform random sampling, and the selected locations showed smaller deviations from the mean and standard deviation of the entire population. The MFM functioned better in the vineyard, where spatial variability was larger than in the orchard. In both plots, the spatial pattern of the selected samples captured the spatial variability of CWSI. MFM can be adjusted and applied using other moments/functionals and may be adopted by other disciplines, particularly in cases where small sample sizes are desired.

The increased use of pesticides across the globe has a major impact on public health. Advanced sensing methods are considered of significant importance to ensure that pesticide use on agricultural products remains within safety limits. This study presents the experimental testing of a hybrid, nanomaterial based gas-sensing array, for the detection of a commercial organophosphate pesticide, towards its integration in a holistic smart-farming tool such as the "gaiasense" system. The sensing array utilizes nanoparticles (NPs) as the conductive layer of the device while four distinctive polymeric layers (superimposed on top of the NP layer) act as the gas-sensitive layer. The sensing array is ultimately called to discern between two gas-analytes: Chloract 48 EC (a chlorpyrifos based insecticide) and Relative Humidity (R.H.) which acts as a reference analyte since is anticipated to be present in real-field conditions. The unique response patterns generated after the exposure of the sensing-array to the two gas-analytes were analysed using a common statistical analysis tool, namely Principal Component Analysis (PCA). PCA has validated the ability of the array to detect, quantify as well as to differentiate between R.H. and Chloract. The sensing array being compact, low-cost and highly sensitive (LOD in the order of ppb for chlorpyrifos) can be effectively integrated with pre-existing crop-monitoring solutions such as the gaiasense.

Farmers can manage their crops and farms better if they can communicate their experiences, both positive and negative, with each other and with experts. Digital agriculture using internet communication technology (ICT) may facilitate the sharing of experiences between farmers themselves and with experts and others interested in agriculture. ICT approaches in agriculture are, however, still out of the reach of many farmers. The reasons are lack of connectivity, missing capacity building and poor usability of ICT applications. We decided to tackle this problem through cost-effective, easy to use ICT approaches, based on infrastructure and services currently available to small-scale producers in developing areas. Working through a participatory design approach, we developed and tested a novel technology. GeoFarmer provides near real-time, two-way data flows that support processes of co-innovation in agricultural development projects. It can be used as a cost-effective ICT-based platform to monitor agricultural production systems with interactive feedback between the users, within pre-defined geographical domains. We tested GeoFarmer in four geographic domains associated with ongoing agricultural development projects in East and West Africa and Latin America. We demonstrate that GeoFarmer is a cost-effective means of providing and sharing opportune indicators of on-farm performance. It is a potentially useful tool that farmers and agricultural practitioners can use to manage their crops and farms better, reduce risk, increase productivity and improve their livelihoods.

We describe in this paper the implementation of E-Water, an open software Decision Support System (DSS), designed to help local managers assess the Water Energy Food Environment (WEFE) nexus. E-Water aims at providing optimal management solutions to enhance food crop production at river basin level. The DSS was applied in the transboundary Mékrou river basin, shared among Benin, Burkina Faso and Niger. The primary sector for local economy in the region is agriculture, contributing significantly to income generation and job creation. Fostering the productivity of regional agricultural requires the intensification of farming practices, promoting additional inputs (mainly nutrient fertilizers and water irrigation) but, also, a more efficient allocation of cropland. In order to cope with the heterogeneity of data, and the analyses and issues required by the WEFE nexus approach, our DSS integrates the following modules: (1) the EPIC biophysical agricultural model; (2) a simplified regression metamodel, linking crop production with external inputs; (3) a linear programming and a multiobjective genetic algorithm optimization routines for finding efficient agricultural strategies; and (4) a user-friendly interface for input/output analysis and visualization. To test the main features of the DSS, we apply it to various real and hypothetical scenarios in the Mékrou river basin. The results obtained show how food unavailability due to insufficient local production could be reduced by, approximately, one third by enhancing the application and optimal distribution of fertilizers and irrigation. That would also affect the total income of the farming sector, eventually doubling it in the best case scenario. Furthermore, the combination of optimal agricultural strategies and modified optimal cropland allocation across the basin would bring additional moderate increases in food self-sufficiency, and more substantial gains in the total agricultural income. The proposed software framework proves to be effective, enabling decision makers to identify efficient and site-specific agronomic management strategies for nutrients and water. Such practices would augment crop productivity, which, in turn, would allow to cope with increasing future food demands, and find a balanced use of natural resources, also taking other economic sectors-like livestock, urban or energy-into account.

Bovine respiratory disease (BRD) complex in calves impairs health and welfare and causes severe economic losses for the Stockperson. Early recognition of BRD should lead to earlier veterinary (antibiotic/anti-inflammatory) treatment interventions thereby reducing the severity of the disease and associated costs. Coughing is one of the clinical manifestations of BRD. It is believed that by automatically and continuously monitoring the sounds within calf houses, and analysing the coughing frequency, early recognition of BRD in calves is possible. Therefore, the objective of the present study was to develop an automated calf cough monitor and examine its potential as an early warning system for BRD in artificially reared dairy calves. The coughing sounds of 62 calves were continuously recorded by a microphone over a three-month period. A sound analysis algorithm was developed to distinguish calf coughs from other sounds (e.g. mechanical sounds). During the sound recording period the health of the calves was assessed and scored periodically per week by a trained human observer. Calves presenting with BRD received antibiotic and/or anti-inflammatory treatment and the dates of treatment were recorded. This treatment date reference served as a comparison for the investigation of whether an increase in coughing frequency could be related to calves developing BRD. The calf cough detection algorithm achieved 50.3% sensitivity, 99.2% specificity and 87.5% precision. Four out of five periods, where coughing frequency was observed to be increased, coincided with the development of BRD in more than one calf. This period of increased coughing frequency was always observed before the calves were treated. Therefore, the calf cough monitor has the potential to identify early onset of BRD in calves.

In commercial poultry production there are a number of diseases which are of particular importance due to the heavy economic losses that can arise if a flock becomes infected. The development of an automated and rapid disease detection system would therefore be of considerable benefit to both production and animal welfare. This study represents an intelligence device for diagnosing avian diseases by using Data-mining methods and Dempster-Shafer evidence theory (D-S). 14-day-old chickens were divided into four groups. Each group was deliberately infected with a disease: Newcastle Disease (ND), Bronchitis Virus (BV), Avian Influenenza (AI), and the last group was considered as control samples. Fast Fourier Transform (FFT) and Discrete Wavelet Transform (DWT) were used to process the chicken's sound signals in frequency and time-frequency domains, respectively. In order to achieve information, 25 statistical features from frequency domains, and 75 statistical features from time-frequency domains were extracted. During dimensionality reduction stage, the best features of the sound signals were selected, using improved distance evaluation (IDE) method. The chicken's sound signals were analyzed in two consecutive days after virus infection. Support vector machine (SVM) was used as the classifier in this study. The first classification was done with SVM and based on sound features in frequency and time-frequency domains with accuracy of 41.35 and 83.33%, respectively. The accuracy of the method based on D-S infusion of sound data reached 91.15%. The developed model based on achievement result could diagnose Newcastle Disease, Bronchitis Virus and Avian Influenza from sound signals.

This paper presents a novel approach to automated classification and quantification of sow postures and posture transitions that may enable large scale and accurate continuous behaviour assessment on farm. Automatic classification and quantification of postures and posture transitions in domestic animals has substantial potential to enhance their welfare and productivity. Analysis of such behaviours in farrowing sows can highlight the need for human intervention or lead to the prediction of movement patterns that are potentially dangerous for their piglets, such as crushing when the sow lies down. Data were recorded by a tri-axial accelerometer secured to the hind-end of each sow, in a deployment that involved six sows over the period around parturition. The posture state (standing, sitting, lateral and sternal lying) was automatically classified for the full dataset with a mean score (a measure of predictive performance between 0 and 1) of 0.78. Sitting was shown to present a greater challenge to classification with a score of 0.54, compared to the lateral lying postures, which were classified with an average score of 0.91. Posture transitions were detected with a  score of 0.79. We automatically extracted and visualized a range of features that characterise the manner in which the sows changed posture in order to provide comparative descriptors of sow activity and lying style that can be used to assess the influence of genetics or housing design. The methodology presented in this paper can be applied in large scale deployments with potential for enhancing animal welfare and productivity on farm.

We developed a simulation model to study the effect of ventilation airflow rate with and without filtered recirculation on airborne contaminant concentrations (dust, NH, CO, and CO) for swine farrowing facilities. Energy and mass balance equations were used to simulate the indoor air quality and operational cost for a variety of ventilation conditions over a 3-month winter period, using time-varied outdoor temperature. The sensitivity of input and output parameters on indoor air quality and operational cost were evaluated. Significant factors affecting model output included mean winter temperature, generation rate of contaminants, pit-air-exchange ratio, and recirculation ratio. As mean outdoor temperature was decreased from -2.5 °C to -12.5 °C, total operational costs were increased from $872 to $1304. Dust generation rate affected dust concentrations linearly. When dust generation rates changed -50% and +100% from baseline, indoor dust concentrations were changed -50% and +100%, respectively. The selection of a pit-air-exchange ratio was found critical to NH concentration, but has little impact on other contaminants or cost. As the pit-air-exchange ratio was increased from 0.1 to 0.3, the NH concentration was increased by a factor of 1.5. The recirculation ratio affected both IAQ factors and total operational cost. As the recirculation ratio decreased to 0, inhalable and respirable dust concentrations, humidity, NH and CO concentrations decreased and total operational cost ($2216) was 104% more than with pit-fan-only ventilation ($1088). When the recirculation ratio was 1, the total operational cost was increased by $573 (53%) compared to pit-fan-only. Simulation provides a useful tool for examining the costs and benefits to installing common ventilation technology to CAFO and, ultimately, making sound management decisions.