Improved Farm Management Research Articles

Farmers’ Perception on Pollinators and Apple Pollination in Western Bhutan

Apples are one of the most important global fruit crops both in terms of yield and economic value, and rely on insect pollination. Pollination has been shown to increase apple production and economic value. The apple production in Bhutan has decreased from 7,051 MT in 2014 to 3,684 MT in 2018. Among the factors identified for the decline of apple quality and yield, pollinator deficits in orchards and inefficient pollination are hypothesised to be less recognised among Bhutanese farmers. Here we surveyed the knowledge and perception of farmers towards apple pollination and pollinators in the three dominant apple-producing districts of Bhutan: Thimphu, Paro, and Haa. One hundred and five farmers (35 from each district) were interviewed using a semi-structured questionnaire. When asked about the yield trend compared to previous years, 74.3% of the respondents noticed a decrease in yield compared to the year 2019, and 96.2% of the respondents said yield has decreased over the last five years. Sixty percent of the farmers were unaware of apple pollination and the importance of pol-linators. The farmers could not differentiate between different pollinator species, with honeybees be-ing the only pollinator known to the farmers. Education and years of working experience were found to influence farmers’ knowledge about pollinators and apple pollination. This study establishes base-line information of farmers’ knowledge in Bhutan, which will be useful to improve farm management practices that will benefit apple quality and productivity, as well as pollinator conservation.

Temporal and spatial variability in hydrography and dissolved oxygen along southwest Nova Scotia using glider observations

Dissolved oxygen (DO) in the global ocean is on the decline, resulting in the degradation of coastal habitats. As aquaculture production occurs in these regions, proper understanding of coastal DO dynamics is important for improved farm management (e.g. site selection). The main objective of this study was to quantify along-shore and cross-shore variability in DO dynamics, as well as onshore advection of offshore waters to the bays that could contain aquaculture farms. For that purpose, a Slocum underwater glider was deployed between September 25 and October 12, 2020 to collect high-resolution data of temperature, salinity and DO along a transect between Shelburne Bay and St. Margarets Bay, Nova Scotia, Canada, with an average distance of about 15 km from shore. The observations revealed the variable nature of cross-shore water properties. Shoreward bottom currents transport offshore waters to the coast, and combined with longer residence times, mixing of these waters with those present created a mosaic of differing water properties, with warmer, fresher, and less oxygenated shoreward waters. The glider intercepted an upwelling event due to strong and persistent southwesterly winds, which cooled the upper water layers by 6 °C and increased DO by 1.4 mg L−1. This strong upwelling event detected at 10 km from the coast was also captured 30 h later within St. Margarets Bay, depicting a potential offshore-inshore interaction. Therefore, bay-wide ecosystems and aquaculture production could be affected by intrusions of offshore waters.

Early Estimation of Tomato Yield by Decision Tree Ensembles

Crop yield forecasting allows farmers to make decisions in advance to improve farm management and logistics during and after harvest. In this sense, crop yield potential maps are an asset for farmers making decisions about farm management and planning. Although scientific efforts have been made to determine crop yields from in situ information and through remote sensing, most studies are limited to evaluating data from a single date just before harvest. This has a direct negative impact on the quality and predictability of these estimates, especially for logistics. This study proposes a methodology for the early prediction of tomato yield using decision tree ensembles, vegetation spectral indices, and shape factors from images captured by multispectral sensors on board an unmanned aerial vehicle (UAV) during different phenological stages of crop development. With the predictive model developed and based on the collection of training characteristics for 6 weeks before harvest, the tomato yield was estimated for a 0.4 ha plot, obtaining an error rate of 9.28%.

Physiological variable predictions using VIS–NIR spectroscopy for water stress detection on grapevine: Interest in combining climate data using multiblock method

In recent years, climate fluctuations have been increasingly extreme, affecting agricultural production. The development of digital agriculture driven by new intelligent sensors is one of the privileged paths to improve farm management. Assessing transpiration E and stomatal conductance gs in real time with optical instruments is a real challenge to detect water stress. In this study, the objective is to evaluate VIS–NIR spectroscopy to predict transpiration E and stomatal conductance gs of grapevine plants (Vitis vinifiera L.). For this purpose, a water stress gradient was obtained using vine pots of three varieties (Syrah, Merlot, Riesling) tested under two water conditions where precise monitoring of physiological variables has been carried out. Hyperspectral images were acquired to form a spectral database and a weather station provided radiation (Rg), relative humidity (RH), temperature (Ta) and wind speed (Ws). First, Partial Least Squares (PLS) models were established to relate spectral data to physiological variables. Then, Sequential Orthogonalized-Partial Least Squares (SO-PLS) was used to predict these physiological variables with two blocks: spectral and climate data. PLS models are obtained for gs (R2= 0.656, bias = 8.76 mmol.m−2.s−1, RMSE = 64.7 mmol.m−2.s−1) and E (R2= 0.625, bias=-0.02 mmol.m−2.s−1, RMSE = 0.67 mmol.m−2.s−1). For E, improved results (R2= 0.699, bias = 0.055 mmol.m−2.s−1, RMSE = 0.614 mmol.m−2.s−1) are obtained by using climate data with SO-PLS. Generic PLS models achieved good predictive quality despite different coloured berry varieties. Quality of these prediction models could be improved by defining varietal models on a larger data set. Merging spectral data with climate data improves prediction quality of transpiration variable providing insights by adding further information with the aim of improving predictive qualities.

Application of Information Technology in the Agriculture Sector of Indian Economy

Agriculture is one of the most important sectors in India and the pillar of the Indian economy. Now it demands the transfer of technologies from lab to land for the second green revolution. Particularly for small and marginal farmers the generation, invention, and application of agricultural knowledge are progressively important, who need relevant information to improve, sustain, and diversify their farm enterprise. Information technology supports new methods and ideas for healthy and precision agriculture. Information technology has the potential tool for improving decision-making in agriculture. IT can improve farm management and farming technologies by efficient farm management. The extensive use of IT to make a direct contribution to agricultural productivity. Satellite technology, geographic information systems using the techniques of agronomy and soil science is to increase agricultural production. In this paper, we study how information technology is helpful for management, improving planning and superior produce of agro products, and the basic issues of information technology in farm practice.

Spatial modelling approach and accounting method affects soil carbon estimates and derived farm-scale carbon payments

Improved farm management of soil organic carbon (SOC) is critical if national governments and agricultural businesses are to achieve net-zero targets. There are opportunities for farmers to secure financial benefits from carbon trading, but field measurements to establish SOC baselines for each part of a farm can be prohibitively expensive. Hence there is a potential role for spatial modelling approaches that have the resolution, accuracy, and estimates to uncertainty to estimate the carbon levels currently stored in the soil. This study uses three spatial modelling approaches to estimate SOC stocks, which are compared with measured data to a 10 cm depth and then used to determine carbon payments. The three approaches used either fine- (100 m × 100 m) or field-scale input soil data to produce either fine- or field-scale outputs across nine geographically dispersed farms. Each spatial model accurately predicted SOC stocks (range: 26.7–44.8 t ha−1) for the five case study farms where the measured SOC was lowest (range: 31.6–48.3 t ha−1). However, across the four case study farms with the highest measured SOC (range: 56.5–67.5 t ha−1), both models underestimated the SOC with the coarse input model predicting lower values (range: 39.8–48.2 t ha−1) than those using fine inputs (range: 43.5–59.2 t ha−1). Hence the use of the spatial models to establish a baseline, from which to derive payments for additional carbon sequestration, favoured farms with already high SOC levels, with that benefit greatest with the use of the coarse input data. Developing a national approach for SOC sequestration payments to farmers is possible but the economic impacts on individual businesses will depend on the approach and the accounting method.

Reducing milking frequency from twice each day to three times each two days affected protein but not fat yield in a pasture-based dairy system

Milking 3 times in 2 d (3-in-2) could enhance the attractiveness of the dairy workplace relative to twice-a-day milking (TAD) by reducing labor requirements for milking and increasing workforce flexibility. The objective of this study was to quantify the farm system interactions associated with milking 3-in-2 at 3 stages of lactation, with the aim of providing guidance to pasture-based dairy farmers and advisors on the likely consequences of adopting 3-in-2 milking on farm productivity and business performance. Seventy-nine multiparous and 37 primiparous cows were randomly allocated to 4 experimental farms stocked at 3.5 cows/ha. One herd was milked TAD for the whole lactation (August 2019 to May 2020), with the remaining 3 milked 3-in-2 for either the whole lactation, after December 1 when cows were an average of 101 d in milk, or after March 1 when days in milk averaged 189 d. Milking intervals over 48 h were 10-14-10-14 h for TAD and 12-18-18 h for 3-in-2. Animal, pasture, and farm system data were analyzed by linear regression, with the dependent variable being the annualized value of the performance metric of interest, and the number of days in the lactation milked 3-in-2 as the independent variable. For the proportion of the season milked 3-in-2, there was a significant effect on milk (-11%), protein (-8%), and lactose (-12%) yield per cow per year, but no effect of fat. Additionally, there was a positive effect (+6%) on body condition score before dry-off and the energy required for liveweight change (+26%), and a negative effect on the energy required for walking (-30%). There were no differences in estimated feed eaten, or pasture herbage accumulation, composition, or quality. Therefore, pasture management and feed allocation under 3-in-2 should be similar to TAD. On commercial farms, the degree to which reduced milk income can be offset by lower costs will be highly farm-specific, but opportunities for savings were identified in the results. The short walking distances on the research farm and potential to improve farm management using the time saved from fewer milkings suggests better production may be achieved with 3-in-2 milking on a commercial farm.

Smart farming technologies adoption: Which factors play a role in the digital transition?

Smart Farming Technologies (SFT) are smart devices part of a cyber-physical system able to improve farm management. Compared to other digital technologies' functionalities, SFT generate a multitude of data that once combined can be used not only on-farm but across the entire supply chain. Although recent studies highlighted how the lack of users’ resources and competences might hinder the diffusion of digital agriculture technologies overall, few studies so far focused specifically on SFT. Moreover, the extant literature interprets the adoption decision mostly as “one-off binary” process, and limited attention is given to individual aspects of users and farms. Therefore, this study investigates the adoption of SFT analyzing various aspects of its complex nature; on the one hand, the analysis considers the multi-step nature of the adoption decision process: first, intention formation and then, actual adoption decision. On the other hand, the SFT adoption process is interpreted as being determined by several typologies of determinants beyond the most studied ones, with a particular focus on the role that organizational conditions and the supply chain governance structure play in influencing farmers' adoption of SFT.An empirical analysis is run on a sample of 474 responses, collected through an on-line survey. Structural Equation Modeling (SEM) and a Zero-Inflated Poisson Regression (ZIP) were used to investigate respectively the intention to use and the actual adoption of SFT. Results show that farmers' intention to use mainly relies on technologies' performance expectancy, technologies' complexity and social influence exerted on farmers, while organizational supporting conditions do not play a significant effect. Nonetheless, when the actual adoption decision is observed, the likelihood that non-adopters intend to adopt SFT in their farms increases when formal integration along the supply chain is high and with the dimension of the farm (in terms of both land size and sales). When the adopters are analyzed instead, the decision to adopt is positively affected only by the individual intention to use and by farmers' specialization in the arable sector.Findings reveal what factors need to be considered to guarantee a fairer and more inclusive agricultural digitalization, such as the role of social influence exerted by some figures around farmers and the still weak facilitating organizational conditions.

Dairy calf and replacement heifer mortality on a single intensively managed dairy farm in Jordan: A 3-year-long study (2016-2018).

Pre-weaning dairy calf and replacement heifer mortality represents significant economic loss, limits genetic improvement and growth of the herd, and indicates poor management and animal welfare status on the farm. Currently, the rates and causes of the dairy calf and replacement heifer mortality in Jordan are not known. Therefore, the objective of this study was to determine the incidence rates and causes of mortality of pre-weaning calves and replacement heifers in Jordan. In addition, the age and seasonal distribution of mortality are determined in the study. Data extracted from the farm management record software over 3 years (January 2016-December 2018) were used in this study. Calf-specific data included the day and month of birth and sex. Health-related data included age at death, necropsy findings, laboratory findings if available, and the presumptive diagnosis. Descriptive analysis was performed to determine the 3-year overall mortality rate as well as the yearly mortality rate in pre-weaning calves and replacement heifers using excel spreadsheets of Microsoft Word 10. Only female calves (n = 724) born alive during the study period were used in the analysis. The overall calf mortality rate was 8.9% with a yearly rate ranging between 5.9% and 12%. The majority of deaths occurred in calves less than 50 days of age with an average age of 17 days. There was a seasonal pattern for calf mortality with the majority of deaths occurring during the colder months of the year (December, January, February, and March). The highest number of pre-weaning calves died because of enterotoxemia (39%) and pneumonia (30%). Other causes of calf mortality were abomasal ulcer (8%), enteritis (6%), septicemic salmonellosis (5%), meningitis (4%), rumen drinkers (3%), aspiration pneumonia (3%), septic arthritis (1%), and omphalitis (1%). The overall 3-year heifer mortality rate was 4%. The average age of dead heifers was 8 months (range 3-23 months). The highest number of heifers died because of neurologic disease (37%) and enterotoxemia (33%). Other causes of heifer mortality were abomasal ulcer (11%), enteric salmonellosis (7%), chronic rumen tympany (7%), and chronic pneumonia (4%). Data presented in this study are essential to construct and implement effective preventative health programs and improve farm management practices to reduce calf and heifer losses.

PRODUCTION INPUTS ALLOCATION AND PERFORMANCE BENCHMARK OF RICE FARMS IN ANAMBRA STATE, NIGERIA

The study analyzed the production input allocation and the performance benchmark of rice farms in Anambra State, Nigeria. Efforts at improving farm management and production notwithstanding, more is yet to be achieved in that regard in Anambra State and Nigeria at large. Past studies concentrated on areas like profitability, resources and production efficiency with little or no focus on benchmarking the production and the pattern of input mix. To achieve the broad objective, four (4) specific objectives were outlined thus: (i) categorized production input patterns based on farm performance and based on expenses (iii) determined a performance standard/ benchmark from the category after identifying the existing standard, (iii) identified the diverse effect of production inputs cost on rice farm output for different production levels, and (v) identify the causal factors of difference in farm performance in the study area. A multi-staged sampling technique was employed in the selection of 120 farms. The study utilized primary data generated by the researcher using structured and pretested questionnaire. Descriptive statistics, net farm income, quantile regression and ANOVA were used for the analysis of the primary data gotten through the administration of a structured questionnaire. The 120 farms were grouped as top performers (40), average performers (40) and below average performers (40). The top performing farms had an average net farm income of N340,305 while the average farms and below average farms had N207,567 and N92,258, respectively. The benchmark standard for rice farms in Anambra State was N390, 500. The basic effects of the cost variables on the farm performance as identified with the quantile regression was that the higher the net farm income, the better the opportunities available to increase performance. The major causal factor of differences in farm outcome were, financial constraints, managerial ability, level of input utilization at the farm level, size of farm, high cost of inputs, pests and diseases, and seasonal variation or climate change. The ANOVA result showed that mean expenditures was not significantly different. The study therefore, recommended that cost management and better production instructions should be taken seriously by the extension agents and government should subsidize agricultural inputs for farmers.

Pheno- and genotypic characterization and identification of novel subtypes of Peste des Petits Ruminants virus in domestic and captive wild goats in Northern Iraq

BackgroundPeste des Petits Ruminants (PPR) is an acute or peracute contagious transboundary viral disease that mainly affects caprine and ovine and causes significant economic impact in developing countries. After two PPR virus outbreaks in 2011 and 2014, an investigation, from August 2015 to September 2016, was carried out in Northern Iraq when an increased morbidity and mortality rates were reported in the domestic and captive wild goats. In the present study, ten domestic goat farms and seven captive wild goat herds located in seven geographical areas of Northern Iraq were clinically, pathologically, serologically and genotypically characterized to determine the prevalence and potential cause of PPR virus outbreak.ResultsThe outbreak occurred with rate of morbidity (26.1%) and mortality (11.1%) in domestic goat farms as compared to captive wild goat herds where relatively high mortality (42.9%) and low morbidity (10.9%) rates were recorded. Based on the clinical symptoms (mucopurulent nasal discharges, ulceration and erosion of oral mucosa, profuse watery diarrhea) and necropsy (hemorrhage and congestion on mucous membranes of the colon and rectum with zebra stripes lesions) results, overall, the serological test findings revealed a high frequency (47.9%) of positive samples for anti-PPRV nucleoprotein antibodies. Furthermore, the nucleoprotein (N) gene was detected in 63.2 and 89.1% of samples using conventional and reverse transcription real-time quantitative PCR assays. A phylogenetic analysis of N gene amino acid sequences clustered with the reference strain revealed lineage IV similar to the strains isolated in 2011 and 2014, respectively. However, two sub-types of lineage IV (I and II), significantly distinct from the previous strains, were also observed.ConclusionThe phylogenetic analysis suggests that movements of goats are possible cause and one of the important factors responsible for the spread of virus across the region. The study results would help in improving farm management practices by establishing a PPR virus eradication program using regular monitoring and vaccination program to control and mitigate the risk of re-emergence of PPR virus infection in domestic and captive wild goats in Iraq.

Bioenergy: a foundation to environmental sustainability in a changing global climate scenario

Bioenergy has obvious advantages over conventional fossil fuels owing to its renewability and huge capacity, which has dominating role in shielding the energy security that can be a favourable alternative to the disruption of food, resources and the atmosphere. In order to maintain their immediate energy levels and restore the atmosphere, coal-based countries need alternative fuels. For example, wonder inclusion to renewable energy are biofuels derived from crop residues devoid of sacrificing on food production. Annually, about 65 million tonnes (or 280 million metric tonnes) of energy crop-based ethanol are generated, which itself is equal to China's present gasoline ethanol output (2 million tonnes per year). The adverse effects of bioenergy production can vary highly depending on biological sources, land locations and management practices. Replacing fossil fuels with biofuels can significantly reduce these harmful effects arising from various fossil fuels. Identifying crop growing areas, appropriate bioenergy cultivars and appropriate management practices will contribute to the rig environment and biochemical sustainable development. Improved farm management and landscape planning are valuable for ecological services. This paper discusses several biofuels induced patterns of land managements, and generations of biofuel resources practices, cultivation of bioenergy crops environmental implications, and prospective techniques for establishing ecologically friendly biomass energy programmes.

Suitability of satellite remote sensing data for yield estimation in northeast Germany

Information provided by satellite data is becoming increasingly important in the field of agriculture. Estimating biomass, nitrogen content or crop yield can improve farm management and optimize precision agriculture applications. A vast amount of data is made available both as map material and from space. However, it is up to the user to select the appropriate data for a particular problem. Without the appropriate knowledge, this may even entail an economic risk. This study therefore investigates the direct relationship between satellite data from six different optical sensors as well as different soil and relief parameters and yield data from cereal and canola recorded by the thresher in the field. A time series of 13 years is considered, with 947 yield data sets consisting of dense point data sets and 755 satellite images. To answer the question of how well the relationship between remote sensing data and yield is, the correlation coefficient r per field is calculated and interpreted in terms of crop type, phenology, and sensor characteristics. The correlation value r is particularly high when a field and its crop are spatially heterogeneous and when the correct phenological time of the crop is reached at the time of satellite imaging. Satellite images with higher resolution, such as RapidEye and Sentinel-2 performed better in comparison with lower resolution sensors of the Landsat series. The additional Red Edge spectral band also has advantage, especially for cereal yield estimation. The study concludes that there are high correlation values between yield data and satellite data, but several conditions must be met which are presented and discussed here.

Climate Smart Actions “Saung Iklim” for Smallholder Farmers in Subang District, West Java, Indonesia

The implementation of climate change adaptation for crop production is often ineffective among farmers due to a lack of access to climatic data and inadequate knowledge on how to use the available data. The project introduced the utilization of climate data via the Climate Smart Action "Saung Iklim" application to targeted stakeholders (i.e., agricultural extension workers and farmer representatives) designed to improve farm management. The term “Saung Iklim” originally means a place where people can learn about the use of climate information for farming activities. Therefore, strengthening stakeholders’ capacity is an essential element of "Saung Iklim", which has been conducted via a series of training activities using various modules and focus group discussions. The project selected one of the major production centres of rice in Indonesia, namely the District of Subang. The district government formed a task force named “Tim Iklim”, consisting of the targeted stakeholders, to assist the project team in delivering the targeted project outputs. The project team, in collaboration with Tim Iklim, produced the modules on utilizing simulations of crop models for managing climate risks. The involvement of the stakeholders was to accommodate their input and understanding so that the modules are ready for practical purposes. The project also equipped Tim Iklim with a dedicated website, containing crop simulation model (CSM) outputs, modules, online surveys, and forums, to facilitate information delivery on managing farm risks to climate exposures.

Climate Change, Mountain Food Systems, and Emerging Opportunities: A Study from the Hindu Kush Karakoram Pamir Landscape, Pakistan

This study investigated the mountain food systems in the Hindu Kush Karakoram Pamir Landscape (HKPL) in Pakistan. It analyzed the impacts of climate change on agriculture and livestock and identified key opportunities which can be tapped into to improve sustainability in food systems. The study applied a “multiple case studies approach” and collected data from four study sites at different altitudes, using the method of slow focus group discussions, key informant interviews, and non-participant observation. Findings revealed that the contribution of local agriculture and livestock to people’s food consumption has gradually declined, increasing their dependence on external food items. Local food systems are losing diversity, which has negatively impacted people’s dietary diversity. The youth has lost interest in agriculture due to low productivity and profitability in a high altitude village—Misgar (≈3200 m above sea level). In all sites, local people perceived mixed impacts (both positive and negative) of climate change on food systems. Climate change together with enhanced use of pesticides and inorganic fertilizers, high yielding seed, and improved farm management have positive, and climate-attributed increase in crop pest attacks has negative impact on crop productivity. Moreover, local people perceived negative impacts of climate change on pastures and water availability in traditional irrigation systems without significant influence on crop and livestock productivity. In food systems, these are needed to maximize benefits from the local potential for organic production, livestock integration, value chain development, traditional food crops, medicinal plants, and protected vegetables cultivation to reduce the vulnerability of food systems to climactic and economic shocks, and improve the sustainability.

System design for inferring colony-level pollination activity through miniature bee-mounted sensors

In digital agriculture, large-scale data acquisition and analysis can improve farm management by allowing growers to constantly monitor the state of a field. Deploying large autonomous robot teams to navigate and monitor cluttered environments, however, is difficult and costly. Here, we present methods that would allow us to leverage managed colonies of honey bees equipped with miniature flight recorders to monitor orchard pollination activity. Tracking honey bee flights can inform estimates of crop pollination, allowing growers to improve yield and resource allocation. Honey bees are adept at maneuvering complex environments and collectively pool information about nectar and pollen sources through thousands of daily flights. Additionally, colonies are present in orchards before and during bloom for many crops, as growers often rent hives to ensure successful pollination. We characterize existing Angle-Sensitive Pixels (ASPs) for use in flight recorders and calculate memory and resolution trade-offs. We further integrate ASP data into a colony foraging simulator and show how large numbers of flights refine system accuracy, using methods from robotic mapping literature. Our results indicate promising potential for such agricultural monitoring, where we leverage the superiority of social insects to sense the physical world, while providing data acquisition on par with explicitly engineered systems.

Understanding antibiotic use for pig farming in Thailand: a qualitative study

BackgroundAntimicrobial resistance (AMR), recognised as a serious and growing threat to global health, is promoted by multiple drivers, including antibiotic use in the livestock sector. Thus, understanding factors influencing antibiotic use in livestock production is essential to the design and implementation of effective interventions to reduce AMR. This qualitative study aimed to explore the experiences and views of the key actors associated with the use of antibiotics for pig farming in Thailand, from local farmers to officers in central government institutions.MethodsA total of 31 in-depth interviews were conducted with different categories of actors: pig farmers (n = 13), drug retailers (n = 5), veterinarians (n = 7), government officers (n = 3) and representatives of animal and human health associations (n = 2). Themes emerging from the interviews were identified and explored using thematic analysis. In addition, direct observations were conducted in the pig farms.ResultsThe findings highlight the multi-faceted nature of the views and practices that may contribute to misuse or overuse of antibiotics in the study locations, including misconceptions about the nature of antibiotics and AMR (particularly among smallholders), lack of facilities and financial means to establish an antibiotic-free farm, lack of sufficient training on AMR and antibiotic prescribing for veterinarians, the profit motive of pharmaceutical companies and their ties to farm consultants, and lack of sufficient regulatory oversight.ConclusionsOur study indicates a clear need to improve antibiotic use for pig production in Thailand. Farmers need better access to veterinary services and reliable information about animal health needs and antibiotics. Innovative investments in biosecurity could improve farm management and decrease reliance on antibiotics, although the cost of these interventions should be low to ensure wide uptake in the livestock sector. Lastly, further development of professional training and clinical guidelines, and the establishment of a code of conduct, would help improve antibiotic dispensing practices.

178 Towards better usage of data in dairy farms: The Dairy Brain initiative

Abstract With increasing use of new technologies in dairy farms, vast amounts of data are generated. Each data stream has its own frequency, diversity, type and quantity of data. While data diversity is beneficial to the farmer, it also makes more difficult data integration of different data streams. Even though different data streams are poorly linked to each other, there is an opportunity to add value to the farm management and decision-making processes by standardizing and integrating the different data sources available at the farm. Therefore, it is imperative to develop a system that can collect, integrate, manage, and analyze on- and off-farm data in real-time for practical and relevant actions: The Dairy Brain project. This is a trans-disciplinary research and extension project that engages multi-disciplinary scientists, dairy farmers, and industry professionals. We are using the state-of-the-art database management system from the University of Wisconsin-Madison Center for High Throughput Computing to develop our Agricultural Data Hub (AgDH) that connects and analyzes cow and herd data on a permanent basis. This involves cleaning and normalizing the data as well as allowing data retrieval on demand.The Dairy Brain, a suite of predictive and prescriptive analytics modules that leverages the AgDH to provide insight to the management of dairy operations and serve as an exemplar of an ecosystem of connected services. Therefore, decision support tools are developed to add value to the data and improve farm management at different levels.

English

Soil salinity is the major factor that limits agricultural productivity in arid and semi-arid regions. The use of improved farm management practices in such areas is becoming a highly concerning issue to sustain agricultural productivity. This study, therefore, was conducted to evaluate the effect of on-farm water management practices and irrigation water sources on soil quality. The experiment was conducted on 16 farmer's fields in the area for two consecutive years. Soil and water sampling were done at the beginning and end of each growing season. Both samples were analyzed for selected parameters following standard laboratory procedures. A general linear model of two ways analysis of variance was used to evaluate the variations among treatments. Results indicated that about 64.3% of studied soil properties are showed significant variation at P<5% across treatments. This implies that management practice and sources of irrigation water have an impact on soil productivity. Salinity and alkalinity values showed an increasing trend over time and higher values for both parameters were observed in groundwater irrigated fields. This suggested that irrigation water sources have also pronounced effects on soil quality. The higher value for soil fertility indicators such as organic carbon, nitrogen, and phosphorous was also observed under managed fields. This also suggests management practices positively influenced soil productivity. Therefore, paying attention to management practices and water quality is very important to maintain soil productivity. Key words: Agriculture, ANOVA, irrigation management, soil salinity, water quality.

383 Harnessing the Power of Computer Vision System to Improve Management Decisions in Livestock Operations

Abstract In livestock operations, systematically monitoring animal body weight, biometric body measurements, animal behavior, feed bunk, and other complex phenotypes is unfeasible due to labor, costs, and animal stress. Applications of computer vision are growing in importance in livestock systems due to their ability to generate real-time, non-invasive, and accurate animal-level information. Such technology has emerged as a powerful tool to predict animal identification, body weight, biometric measurements, complex behavioral traits, and feed bunk score. However, the development of a computer vision system requires sophisticated statistical and computational approaches for efficient data management and appropriate data mining, as it involves massive datasets. The objective of this talk is to provide an overview of how computer vision systems can be an effective tool to integrate animal-level information and to create predictive modeling for precise management decisions. We will discuss some of the challenges, applications, and potentials of computer vision systems in livestock, and some examples to be presented include: (1) monitoring animal growth and behavior; (2) automated feed bunk management; (3) individual animal recognition; and (4) particle size distribution in total mixed ration. The development of computer vision technologies will potentially have a major impact in the livestock industry by predicting real-time and accurate phenotypes, which, in the future, could be used to improve farm management decisions, breeding programs, and to build optimal data-driven interventions.