Artificial Intelligence in Digital Agriculture. Towards In-Field Grapevine Monitoring using Non-invasive Sensors
Agriculture seeks for a reduction of costs and environmental impact, better sustainability and to increase crop yield and quality. It is necessary to deliver useful applications for farmers and industries, to help for greater efficiency and sustainability. To achieve this in digital viticulture, use...
Guardado en:
| Autor principal: | |
|---|---|
| Otros Autores: | |
| Formato: | text (thesis) |
| Lenguaje: | eng |
| Publicado: |
Universidad de La Rioja (España)
2019
|
| Acceso en línea: | https://dialnet.unirioja.es/servlet/oaites?codigo=231534 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| id |
oai-TES0000022902 |
|---|---|
| record_format |
dspace |
| institution |
DialNet |
| collection |
DialNet |
| language |
eng |
| description |
Agriculture seeks for a reduction of costs and environmental impact, better sustainability and to increase crop yield and quality. It is necessary to deliver useful applications for farmers and industries, to help for greater efficiency and sustainability. To achieve this in digital viticulture, useful information about the vineyard is necessary so better decisions can be taken. Advances in non-invasive sensing technologies allow the acquisition of high amounts of data from the vineyard, but these data alone are not enough to be used when decisions need to be made, it needs to be transformed into information. Artificial intelligence is a revolution at different social, work and industrial levels to deal with data. Within artificial intelligence, machine learning has evolved greatly during the last decades providing tools to make computers learn, and these algorithms are used in many different fields due to their high versatility for many data-related tasks, generating knowledge and information, and improving the decision-making process. Therefore, the combination of non-invasive sensors and artificial intelligence needs to be explored to meet the requirements needed to apply digital agriculture, the data-driven agriculture.
The main objective of this PhD Thesis is the combination of machine learning and non-invasive sensing technologies for the assessment of relevant agronomical, physiological and qualitative traits in digital agriculture and viticulture. Specifically, the following objectives have been pursued: i) to make use of different machine learning algorithms on data from spectroscopy for in-field grapevine phenotyping and monitoring; ii) the application of ensemble data analysis techniques for vineyard water status assessment with thermal imaging; and iii) to deploy hyperspectral imaging in the field, supported by intensive machine learning combinations, for the monitoring of different crop traits. The first objective, covered in Chapter 3, was the combination of machine learning algorithms and near-infrared spectroscopy for vineyard monitoring and phenotyping. A handheld spectrometer was used for two goals: the classification of grapevine varieties, from several vineyard plots and vintages; and water status assessment, using the same spectral signal. Accurate models were developed for both goals. The results allow to open new ways in digital viticulture for the quick grapevine phenotyping under field conditions, an useful tool for several actors in the wine industry.
The application of ensemble machine learning algorithms to in-field thermal images acquired on-the-go for vineyard water status monitoring, the second objective, is addressed in Chapter 4. A thermal camera was mounted on an all-terrain vehicle for continuous acquisition. A combination of rotation forests and decision trees was used for the training of prediction models. The outcomes provided by the machine learning algorithms support the use of thermal imaging for fast, reliable estimation of a vineyard water status, even suppressing the necessity of supervised acquisition of reference temperatures. The new developed on-the-go method can be very useful in the grape and wine industry for assessing and mapping vineyard water status.
The last objective was the use of on-the-go hyperspectral imaging under field conditions, modelled with machine learning techniques, and it is discussed in Chapter 5. Hyperspectral imaging is a powerful technology, but it has been classically used under laboratory conditions. Very few attempts on in-field hyperspectral imaging have been reported in the literature, due to the difficulties, like natural, irregular illumination or unknown a priori sample positioning in the recorded scene, that it is necessary to face. For this reason, a considerable amount of the work developed in this PhD Thesis has been focused on surpassing the challenges that come from deploying a hyperspectral camera in the field for the on-the-go vineyard monitoring. Also, as hyperspectral imaging involves the management of a high amount of data, advanced machine learning algorithms become appealing to be applied in this scenario. Three different applications were developed: varietal classification, grape composition assessment and yield estimation. In all of them, it was designed a mechanism for the automated identification of the different grapevine organs. Potent models were obtained for the monitoring of different key viticulture and agriculture parameters. The results suggest that machine learning and hyperspectral imaging can be used to accurately estimate several traits in vineyards and other crops, becoming a powerful and accurate tool in the decision making process.
The results from the research work carried out in this PhD Thesis, also published in several scientific articles, demonstrated that artificial intelligence techniques are able to exploit the potential of data acquired using non-invasive sensing technologies for the monitoring and phenotyping of key crop traits. This can be of utmost importance in digital agriculture and viticulture as new solutions can be developed as decision support tools. |
| author2 |
Diago Santamaría, María Paz (null) |
| author_facet |
Diago Santamaría, María Paz (null) Gutiérrez Salcedo, Salvador |
| format |
text (thesis) |
| author |
Gutiérrez Salcedo, Salvador |
| spellingShingle |
Gutiérrez Salcedo, Salvador Artificial Intelligence in Digital Agriculture. Towards In-Field Grapevine Monitoring using Non-invasive Sensors |
| author_sort |
Gutiérrez Salcedo, Salvador |
| title |
Artificial Intelligence in Digital Agriculture. Towards In-Field Grapevine Monitoring using Non-invasive Sensors |
| title_short |
Artificial Intelligence in Digital Agriculture. Towards In-Field Grapevine Monitoring using Non-invasive Sensors |
| title_full |
Artificial Intelligence in Digital Agriculture. Towards In-Field Grapevine Monitoring using Non-invasive Sensors |
| title_fullStr |
Artificial Intelligence in Digital Agriculture. Towards In-Field Grapevine Monitoring using Non-invasive Sensors |
| title_full_unstemmed |
Artificial Intelligence in Digital Agriculture. Towards In-Field Grapevine Monitoring using Non-invasive Sensors |
| title_sort |
artificial intelligence in digital agriculture. towards in-field grapevine monitoring using non-invasive sensors |
| publisher |
Universidad de La Rioja (España) |
| publishDate |
2019 |
| url |
https://dialnet.unirioja.es/servlet/oaites?codigo=231534 |
| work_keys_str_mv |
AT gutierrezsalcedosalvador artificialintelligenceindigitalagriculturetowardsinfieldgrapevinemonitoringusingnoninvasivesensors |
| _version_ |
1718346679168532480 |
| spelling |
oai-TES00000229022019-08-21Artificial Intelligence in Digital Agriculture. Towards In-Field Grapevine Monitoring using Non-invasive SensorsGutiérrez Salcedo, SalvadorAgriculture seeks for a reduction of costs and environmental impact, better sustainability and to increase crop yield and quality. It is necessary to deliver useful applications for farmers and industries, to help for greater efficiency and sustainability. To achieve this in digital viticulture, useful information about the vineyard is necessary so better decisions can be taken. Advances in non-invasive sensing technologies allow the acquisition of high amounts of data from the vineyard, but these data alone are not enough to be used when decisions need to be made, it needs to be transformed into information. Artificial intelligence is a revolution at different social, work and industrial levels to deal with data. Within artificial intelligence, machine learning has evolved greatly during the last decades providing tools to make computers learn, and these algorithms are used in many different fields due to their high versatility for many data-related tasks, generating knowledge and information, and improving the decision-making process. Therefore, the combination of non-invasive sensors and artificial intelligence needs to be explored to meet the requirements needed to apply digital agriculture, the data-driven agriculture. The main objective of this PhD Thesis is the combination of machine learning and non-invasive sensing technologies for the assessment of relevant agronomical, physiological and qualitative traits in digital agriculture and viticulture. Specifically, the following objectives have been pursued: i) to make use of different machine learning algorithms on data from spectroscopy for in-field grapevine phenotyping and monitoring; ii) the application of ensemble data analysis techniques for vineyard water status assessment with thermal imaging; and iii) to deploy hyperspectral imaging in the field, supported by intensive machine learning combinations, for the monitoring of different crop traits. The first objective, covered in Chapter 3, was the combination of machine learning algorithms and near-infrared spectroscopy for vineyard monitoring and phenotyping. A handheld spectrometer was used for two goals: the classification of grapevine varieties, from several vineyard plots and vintages; and water status assessment, using the same spectral signal. Accurate models were developed for both goals. The results allow to open new ways in digital viticulture for the quick grapevine phenotyping under field conditions, an useful tool for several actors in the wine industry. The application of ensemble machine learning algorithms to in-field thermal images acquired on-the-go for vineyard water status monitoring, the second objective, is addressed in Chapter 4. A thermal camera was mounted on an all-terrain vehicle for continuous acquisition. A combination of rotation forests and decision trees was used for the training of prediction models. The outcomes provided by the machine learning algorithms support the use of thermal imaging for fast, reliable estimation of a vineyard water status, even suppressing the necessity of supervised acquisition of reference temperatures. The new developed on-the-go method can be very useful in the grape and wine industry for assessing and mapping vineyard water status. The last objective was the use of on-the-go hyperspectral imaging under field conditions, modelled with machine learning techniques, and it is discussed in Chapter 5. Hyperspectral imaging is a powerful technology, but it has been classically used under laboratory conditions. Very few attempts on in-field hyperspectral imaging have been reported in the literature, due to the difficulties, like natural, irregular illumination or unknown a priori sample positioning in the recorded scene, that it is necessary to face. For this reason, a considerable amount of the work developed in this PhD Thesis has been focused on surpassing the challenges that come from deploying a hyperspectral camera in the field for the on-the-go vineyard monitoring. Also, as hyperspectral imaging involves the management of a high amount of data, advanced machine learning algorithms become appealing to be applied in this scenario. Three different applications were developed: varietal classification, grape composition assessment and yield estimation. In all of them, it was designed a mechanism for the automated identification of the different grapevine organs. Potent models were obtained for the monitoring of different key viticulture and agriculture parameters. The results suggest that machine learning and hyperspectral imaging can be used to accurately estimate several traits in vineyards and other crops, becoming a powerful and accurate tool in the decision making process. The results from the research work carried out in this PhD Thesis, also published in several scientific articles, demonstrated that artificial intelligence techniques are able to exploit the potential of data acquired using non-invasive sensing technologies for the monitoring and phenotyping of key crop traits. This can be of utmost importance in digital agriculture and viticulture as new solutions can be developed as decision support tools.En la agricultura se busca una reducción de costes y de impacto ambiental, mejor sostenibilidad y un incremento de la calidad y el rendimiento del cultivo. Es necesario desarrollar aplicaciones útiles para agricultores que ayuden en esta mejora de eficiencia y sostenibilidad. Para lograr este objetivo en el ámbito de la viticultura, se necesita información sobre el viñedo que puede utilizarse para tomar mejores decisiones. Los nuevos avances en tecnologías de sensórica no invasiva permiten la adquisición de grandes cantidades de datos del viñedo. Sin embargo, los datos por si solos no sirven cuando se tienen que tomar decisiones, ya que tienen que ser convertidos en información. La inteligencia artificial supone una revolución a distintos niveles sociales, de trabajo e industriales. Dentro de la inteligencia artificial, el aprendizaje automático ha evolucionado ampliamente durante las últimas décadas para proveer de herramientas que permitan a los ordenadores aprender. Por su gran versatilidad, estos algoritmos se utilizan en muchos campos distintos donde es necesario trabajar con datos, generando conocimiento e información, y mejorando el proceso de toma de decisiones. Por estos motivos, se debe explorar la combinación de sensores no invasivos con inteligencia artificial para alcanzar los requisitos exigidos en agricultura digital. El objetivo principal de esta tesis doctoral es lograr la combinación de aprendizaje automático y tecnologías de sensórica no invasiva para la estimación de importantes características agronómicas, fisiológicas y cuantitativas en agricultura y viticultura digital. En concreto, se plantearon los siguientes objetivos específicos: i) utilizar diferentes algoritmos de aprendizaje automático sobre datos espectrales para la monitorización y fenotipado en campo de la vid; ii) la aplicación de métodos combinados de análisis de datos para la eslimación del estado hídrico del viñedo con termografía; y iii) utilizar imagen hiperespectral en condiciones de campo, junto con la aplicación intensiva de aprendizaje automático, para la monitorización de distintos aspectos del cultivo. El primer objetivo, cubierto en el Capítulo 3, fue la combinación de algoritmos de aprendizaje automático y espectroscopia de infrarrojo cercano para la monitorización y fenolipado de la vid. Se usó un espectrómetro portátil con dos fines: la clasificación de variedades de vid, con datos de distintos viñedos y campañas; y la estimación del estado hidrico, utilizando la misma señal espectral. Se desarrollaron modelos con gran precisión para ambos objetivos. Los resultados abren nuevas vías en viticultura digital para el fenotipado rápido de la vid bajo condiciones de campo, una herramienta muy útil para varios actores en la industria vitivinícola. El segundo objetivo fue la aplicación de métodos combinados de aprendizaje automático sobre imágenes térmicas adquiridas bajo condiciones de campo para la monitorización en continuo del estado hidrico del viriedo, que se trata en el Capítulo 4. Se instaló una cámara térmica en un quad para realizar captura de datos en continuo. El entrenamiento de los modelos de predicción se llevó a cabo mediante una combinación de rotation forests y árboles de decisión. Los resultados evidencian el uso de termografía para la estimación rápida y fiable del estado hídrico de un viñedo, incluso prescindiendo de la necesidad de medir temperaturas de referencia. El nuevo método desarrollado en continuo puede ser muy úlil en la industria vitivinícola para medir el estado hídrico de un viñedo y generar mapas de variabilidad espacial. El último objetivo, discutido en el Capitulo 5, fue el uso de imagen hiperespectral en continuo en condiciones de campo y modelada con técnicas de aprendizaje automático. Se pueden encontrar muy pocos trabajos que traten sobre el uso de imagen hiperespectral en campo, debido a las dificultades que esta configuración puede presentar, como una iluminación natural e irregular, o la localización a priori desconocida de las muestras en la escena. Por esta razón, gran parte de los esfuerzos dedicados en el periodo de investigación y desarrollo de esta tesis se han dedicado superar el reto de llevar una cámara hiperespectral a campo para la medición en continuo del viñedo, superando los inconvenientes a los que hay que enfrentarse en el nuevo escenario y diseñando aplicaciones útiles para viticultura digital. Se desarrollaron tres aplicaciones distintas: la clasificación de variedades, la evaluación de la composición de los frutos y la estimación del rendimiento. Se obtuvieron modelos precisos para la estimación de estas características del cultivo. Estos resultados sugieren que la imagen hiperespectral puede emplearse para estimar distintos aspectos del viñedo y otros frutales, convirtiéndose en una herramienta potente y precisa para la toma de decisiones. Los resultados del trabajo de investigación llevado a cabo en esta tesis doctoral, publicados en varios articulas científicos, demuestran que las técnicas de inteligencia artificial pueden sacar provecho de datos vegetativos capturados a través de tecnologías de sensórica no invasiva, para caracterizar parámetros clave del cultivo. Estos resultados pueden ser de gran importancia en agricultura y viticultura digital, dado que permiten el desarrollo de nuevas soluciones y herramientas de apoyo a decisiones en la industria agrícola.Universidad de La Rioja (España)Diago Santamaría, María Paz (null)Tardáguila Laso, Javier (null)2019text (thesis)application/pdfhttps://dialnet.unirioja.es/servlet/oaites?codigo=231534engLICENCIA DE USO: Los documentos a texto completo incluidos en Dialnet son de acceso libre y propiedad de sus autores y/o editores. Por tanto, cualquier acto de reproducción, distribución, comunicación pública y/o transformación total o parcial requiere el consentimiento expreso y escrito de aquéllos. Cualquier enlace al texto completo de estos documentos deberá hacerse a través de la URL oficial de éstos en Dialnet. Más información: https://dialnet.unirioja.es/info/derechosOAI | INTELLECTUAL PROPERTY RIGHTS STATEMENT: Full text documents hosted by Dialnet are protected by copyright and/or related rights. This digital object is accessible without charge, but its use is subject to the licensing conditions set by its authors or editors. Unless expressly stated otherwise in the licensing conditions, you are free to linking, browsing, printing and making a copy for your own personal purposes. All other acts of reproduction and communication to the public are subject to the licensing conditions expressed by editors and authors and require consent from them. Any link to this document should be made using its official URL in Dialnet. More info: https://dialnet.unirioja.es/info/derechosOAI |