Submitted by Filipe dos Santos (fsantos@pucsp.br) on 2018-12-14T11:45:48Z No. of bitstreams: 1 Lenilson Lemos Vilas Boas.pdf: 4297593 bytes, checksum: 1aa03b41410e014c8021095ee73b5e7b (MD5) / Made available in DSpace on 2018-12-14T11:45:48Z (GMT). No. of bitstreams: 1 Lenilson Lemos Vilas Boas.pdf: 4297593 bytes, checksum: 1aa03b41410e014c8021095ee73b5e7b (MD5) Previous issue date: 2018-11-26 / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior - CAPES / Systems that use Computer Vision Application Program Interfaces (APIs) can learn and identify patterns and thus perform associations to retrieve additional data. They are able to obtain results much faster than any human agent is. The study uses three computational vision APIs and evaluates their application in the identification of four plant leave diseases. Based on a corpus of fifty images, the API training was conducted in two stages, the first with thirty images and the second training with twenty more images. After the two trainings, the results of the diseases were collected for each API studied, which made it possible to evaluate the identification capacity and its evolution of learning after each training. The results corroborated the hypothesis. They gave evidence of the feasibility of identification of plant leaf diseases by means of computer vision APIs / Sistemas que utilizam APIs (Interfaces de Programação de Aplicação) de visão computacional têm a capacidade de aprender e identificar padrões, e assim realizar associações com outros resultados, sendo capaz de apresentar resultados mais rápidos do que uma pessoa. O trabalho identificou três APIs de visão computacional e avaliou sua aplicação na identificação de doenças em folhas de plantas, comparando os resultados de quatro diferentes doenças de plantas. Os treinamentos das APIs foram realizados em duas etapas, sendo o primeiro treinamento com uma quantidade de imagens e o segundo treinamento adicionando mais imagens. Após os dois treinamentos foram coletados os resultados das doenças para cada API estudada, sendo possível avaliar a capacidade de identificação e sua evolução de aprendizado após cada um dos treinamentos. Os resultados obtidos corroboram as expectativas, apontando para a viabilidade de identificação de doenças em folhas de plantas através de APIs de visão computacional

Orientador: Carlos Eduardo Angeli Furlani / Resumo: A agricultura digital tem contribuído com a melhoria da eficiência na aplicação de insumos ou no plantio em local pré-determinado, resultando no aumento da produtividade. Nesta realidade a aplicação de técnicas de Processamento de Imagens Digitais, bem como a utilização de sistemas que utilizam a Inteligência Artificial, tem ganhado cada vez mais a atenção de pesquisadores que buscam a sua aplicação nos mais diversos meios. Com o objetivo de desenvolver um sistema robótico que utiliza um sistema de visão computacional capaz analisar uma imagem e, detectar basicamente a presença de cana-de-açúcar e planta daninha, bem como a ausência de qualquer planta, o projeto desenvolvido unificou conhecimentos sobre estas duas áreas da ciência da computação com a área de robótica e agricultura que, culminou no desenvolvimento de uma estrutura robótica com ferramentas gratuitas, como é o caso dos softwares e hardwares modulares voltados para o ensino de informática em escolas. A união de tudo isso resultou em uma estrutura de software e hardware que captura e armazena imagens em um banco de dados; além de possibilitar a classificação de imagens pelos usuários habilitados por meio de aplicativo Android. Por meio da verificação da acurácia entregue pelos algoritmos de Machine Learning, com injeção cíclica e, pela análise do tempo de resposta, foi constatado que o sistema é capaz, munido destas informações, de gerar classificadores que, remotamente são carregados pelo DRR (Dispositivo Robótic... (Resumo completo, clicar acesso eletrônico abaixo) / Abstract: Digital agriculture has contributed to improving efficiency in the application of inputs or planting in a predetermined location, resulting in increased productivity. In this reality, the application of Digital Image Processing techniques, as well as the use of systems that use Artificial Intelligence, has increasingly gained the attention of researchers who seek their application in the most diverse media. In order to develop a robotic system capable of creating a computer vision system capable of analyzing an image and basically detecting the presence of sugarcane and weed, as well as the absence of any plant, the project developed unified knowledge on these two areas of computer science with the area of robotics and agriculture, which culminated in the development of a robotic structure with free tools, such as software and modular hardware aimed at teaching computer science in schools. The combination of all this resulted in a software and hardware structure capable of allowing the capture and storage of images in a database; in addition to enabling the classification of images by users enabled through the Android application. By checking the accuracy delivered by the Machine Learning algorithms with cyclic injection and analyzing the response time, it was found that the system was able, with this information, to generate classifiers that are remotely loaded by the RRD and these, in turn, were able to classify images in sugarcane fields in real time. / Mestre

<div>The demand for customized farm management prescription is increasing in order to maximize crop yield and minimize environmental risks under a changing climate. One great challenge to modeling crop growth and production is spatial and temporal variability. The goal of this dissertation research is to use publicly available Landsat imagery, ground samples and historical yield data to establish methodologies to spatially quantify cover crop growth and in-season maize yield. First, an investigation was conducted into the feasibility of using satellite remote sensing and spatial interpolation with minimal ground samples to rapidly estimate season-specific cover crop biomass and N uptake in the small watershed of Lake Bloomington in Illinois. Results from this study demonstrated that remote sensing indices could capture the spatial pattern of cover crop growth as affected by various cover crop and cash crop management systems. Soil adjusted vegetation index (SAVI), enhanced vegetation index (EVI) and triangular vegetation index (TVI) were strongly correlated with cover crop biomass and N uptake for low and moderate biomass and N uptake ranges (0-3000 kg ha-1 and 0-100 kg N ha-1). The SAVI estimated cover crop biomass and N uptake were +/- 15% of observed value. Compared to commonly used spatial interpolation methods such as ordinary kriging (OK) and inverse distance weighting (IDW), using the SAVI method showed higher prediction R2 values than that of OK and IDW. An additional advantage for these remote sensing vegetation indices, especially in the context of diverse agronomic management practices, is their much lower labor requirements compared to the high density ground samples needed for a spatial interpolation analysis. </div><div>In the second study, a new approach using the multivariate spatial autoregressive (MSAR) model was developed at 10-m grid resolution to forecast maize yield using historical grain yield data collected at farmers’ fields in Central Indiana, publicly available Landsat imagery, top 30 cm soil organic matter and elevation, while accounting for yield spatial autocorrelation. Relative mean error (RME) and relative mean absolute error (RMAE) were used to quantify the model prediction accuracy at the field level and 10-m grid level, respectively. The MSAR model performed reasonably well (absolute RME < 15%) for field overall yield predictions in 32 out of 35 site-years on the calibration dataset with an average absolute RME of 6.6%. The average RMAE of the MSAR model predictions was 13.1%. It was found that the MSAR model could result in large estimation error under an extreme stressed environment such as the 2012 drought, especially when grain yield under these stressed conditions was not included in the model calibration step. In the validation dataset (n=82), the MSAR model showed good prediction accuracy overall (± 15% of actual yield in 56 site-years) in new fields when extreme stress was not present. The novel approach developed in this study demonstrated its ability to use elevation and soil information to interpret satellite observations accurately in a fine spatial scale. </div><div>Then we incorporated the MSAR approach into a process-based N transformation model to predict field-scale maize yield in Indiana. Our results showed that the linear agreement of predicted yield (using the N Model in the Mapwindow GIS + MMP Tools) to actual yield improved as the spatial aggregation scale became broader. The proposed MSAR model used early vegetative precipitation, top 30 cm soil organic matter and elevation to adjust the N Model yield prediction in 10-m grids. The MSAR adjusted yield predictions resulted in more cases (77%) that fell within 15% of actual yield compared to the N Model alone using the calibration dataset (n=35). However, if the 2012 data was not included in the MSAR parameter training step, the MSAR adjusted yield predictions for 2012 were not improved from the N Model prediction (average RME of 24.1%). When extrapolating the MSAR parameters developed from 7 fields to a dataset containing 82 site-years on 30 different fields in the same region, the improvement from the MSAR adjustment was not significant. The lack of improvement from the MSAR adjustment could be because the relationship used in the MSAR model was location specific. Additionally, the uncertainty of precipitation data could also affect the relationship. </div><div>Through the sequence of these studies, the potential utility of big data routinely collected at farmers’ fields and publicly available satellite imagery has been greatly improved for field-specific management tools and on-farm decision-making. </div>

<p>Information about the conditions of specific fields and assets is critical for farm managers to make operational decisions. Location, rainfall, windspeed, soil moisture, and temperature are examples of metrics that influence the ability to perform certain tasks. Monitoring these events in real time and being able to store historical data can be done using Internet of Things (IoT) devices such as sensors. The abilities of this technology have previously been communicated, yet few farmers have adopted these connected devices into their work. A lack of reliable internet connection, the high annual cost of current on-market systems, and a lack of technical awareness have all contributed to this disconnect. One technology that can better meet the demand of farmers is LoRaWAN because of its long range, low power, and low cost. To assist farmers in implementing this technology on their farms the goal was to build a LoRaWAN network with several sensors to measure metrics such as weather data, distribute these systems locally, and provide context to the operation of IoT networks. By leveraging readily available commercial hardware and opens source software two examples of standalone networks were created with sensor data stored locally and without a dependence on internet connectivity. The first use case was a kit consisting of a gateway and small PC mounted to a tripod with 6 individual sensors and cost close to $2200 in total. An additional design was prepared for a micro-computer-based version using a Raspberry Pi, which made improvements to the original design. These adjustments included a lower cost and complication of hardware, software with more open-source community support, and cataloged steps to increase approachability. Given outside factors, the PC architecture was chosen for mass distribution. Over one year, several identical units were produced and given to farms, extension educators, and vocational agricultural programs. From this series of deployments, all units survived the growing season without damage from the elements, general considerations about the chosen type of sensors and their potential drawbacks were made, the practical observed average range for packet acceptance was 3 miles, and battery life among sensors remained usable after one year. The Pi-based architecture was implemented in an individual use case with instructions to assist participation from any experience level. Ultimately, this work has introduced individuals to the possibilities of creating and managing their own network and what can be learned from a reasonably simple, self-managed data pipeline.</p>

<p>    </p> <p>This study’s purpose is to examine the relationship between broadband and online agriculture job postings. While rural broadband has been a wide studied topic, little attention has been focused on broadband’s relationship to agricultural job demand. This research uses a spatial count model that estimates agriculture and digital agriculture jobs by U.S. counties. Data was collected using the Google Jobs API developed by SerpAPI. Job advertisements were collected monthly from June 2021 through June 2022 and again in November 2022. Digital agriculture jobs postings were extracted as a subset from the overall dataset. By searching for key terms in job advertisements, context analysis filtered and identified digital agriculture jobs. Digital agriculture job openings were identified in order to examine how broadband relates to data intensive jobs in agriculture. Jobs focused in digital agriculture require increased levels of technology and increased data throughput. We hypothesized that occurrences of digital agriculture job openings would likely be reliant on broadband. Broadband data in this study represents average download speeds, average upload speeds, the percentage of households with internet access, and the percentage of the population with internet speeds at and above 100 over 20 megabits per second. The approach for modeling this data requires a hurdle negative binomial regression model as our count data encountered many zero observations and suffered from overdispersion. Spatial effects were incorporated into the model to alleviate spatial autocorrelation and help define agricultural job openings among surrounding counties. Our findings support the funding of broadband policies in agriculture. While controlling for outside factors such as demographics and county production, we found that agriculture job openings were positively influenced by broadband. However, we determined that broadband metrics show no relationship with the presence of digital agriculture job openings likely due to rarity and potential seasonality in the data. This information aids as a steppingstone for increasing the knowledge of broadband’s impact on agriculture. This study may aid in supporting future studies that seek to define causal relationships between broadband and agriculture jobs. </p>

The food production rate is required to increase in order to meet the ever-increasing world population. At the same time, this needs to be done in a sustainable manner as the agriculture sector today is responsible for a substantial part of the annual carbon dioxide emissions associated with human activities. In this study, eight farmers in the Swedish agricultural sector whose businesses are primarily based on cultivation and crop production, were interviewed. This to get an understanding of farmers ́ view on connectivity and data, and how this could enable a more productive and sustainable sector in the future.  The study has identified future scenarios that have the potential of contributing to a sustainable development of the sector which are enabled by data and a more connected agriculture sector. One scenario is about fleets of small, connected autonomous agricultural units enabling the electrification transformation of the sector. This will allow for small-scale farms focusing on quality to have great positive impact on the food supply and the sustainability development of the sector. A second scenario is to, with the help of data, make it easier to establish a true consumer value for sustainable products or those of good quality and thereby enable consumers to budget their environmental impact related to food from arable land. In order for this to become feasible a third scenario is related to the agricultural ecosystem which needs to come together and find solutions for data management, creating systems for data handling and analytics to be used both by the farmers and decision makers. With this in place a fourth scenario will be feasible where laws, regulations, and subsidies of today could transform from a generic approach into a more area-based system taking local conditions, determined by data, from individual farms into consideration. There are few contradictions between sustainability and profitability from a farmer ́s point of view and with the help of data and a more connected agriculture, the sector could develop in a positive direction and increase the food production in a sustainable manner. / Produktionen av livsmedel behöver öka för att möta den ständigt ökande världsbefolkningen. Samtidigt måste detta göras på ett hållbart sätt, eftersom jordbrukssektorn redan idag bidrar med en betydande del av de årliga koldioxidutsläppen från mänskliga aktiviteter. I den här studien intervjuades åtta jordbrukare i den svenska jordbrukssektorn med inriktning på odling och produktion av grödor. Detta för att få en förståelse för jordbrukarnas syn på uppkoppling och data, samt hur detta skulle möjliggöra en mer produktiv och hållbar sektor i framtiden.  Studien har identifierat några framtidsscenarier som har potential att bidra till en hållbar utveckling av sektorn och som möjliggörs av data och en mer kopplad jordbrukssektor. Ett scenario handlar om flottor av små, uppkopplade autonoma jordbruksenheter som i sin tur möjliggör en elektrifieringstransformation av sektorn. Detta gör det möjligt för småskaliga jordbruk med fokus på kvalitet att få stor positiv inverkan på livsmedelsförsörjningen och jordbrukssektorns hållbarhetsutveckling. Ett andra scenario är att med hjälp av data göra det lättare att skapa ett verkligt konsumentvärde för hållbara produkter eller produkter av god kvalitet och därigenom göra det möjligt för konsumenterna att budgetera sin miljöpåverkan relaterad till mat från åkermark. För att detta ska bli verklighet krävs ett tredje scenario som innebär att ekosystemet inom jordbrukssektorn måste komma samman och hitta lösningar för datahantering, skapa system för dataanvändning och analys som i sin tur blir användbar både av jordbrukare och beslutsfattare. Med detta på plats kommer ett fjärde scenario att vara genomförbart där dagens generiska lagar, regleringar och subventioner kan förvandlas till ett mer områdesbaserat system där direkt hänsyn kan tas till lokala förhållanden, baserat på data från enskilda gårdar. Det finns få motsättningar mellan hållbarhet och lönsamhet ur jordbrukarnas synvinkel och med hjälp av data och ett mer uppkopplat jordbruk kan sektorn utvecklas i en positiv riktning och öka livsmedelsproduktionen på ett hållbart sätt.