•A systematic review identifies 259 precision agriculture-related publications.•Remote sensors are the most used technology in precision agriculture.•Precision agriculture has been most researched in ...corn, sugarcane and wheat crops.•Factors for deciding what technologies to use for which crops were identified.•No tool that supports the decision of what technology to implement was found.
Agriculture production highly depends on water and soil factors which increasingly need to be utilized efficiently. Precision agriculture, through the set of information technologies that it uses, allows to effectively manage these resources. This work aims to gather the existing knowledge on technologies used in precision agriculture and ways to discern the most appropriate one for different contexts in agricultural processes. A systematic literature review is performed to identify precision agriculture implementations and to answer questions such as the type of technologies used, criteria for their comparison and selection, and the existence of frameworks that help to decide what technologies to implement. A total of 3,949 publications were reviewed, of which 259 addressed the posed research questions. The findings are that remote sensors are the most used technology, the required knowledge is an important criterion for deciding to implement precision agriculture, and no framework was found that guides its implementation.
•The open-source R package bibliometrix is used to conduct a literature review.•A literature review and content analysis of deep learning in agriculture was completed.•A bibliometric overview of ...research on the application of deep learning and in precision agriculture is presented.•Deep learning is widely involved in the digitalization of agriculture.•A literature review allowed the identification of research topics in precision agriculture.•Deep learning is a development factor for precision agriculture.•Deep learning can improve the performance of farms.
Recent advances in communication technologies with the emergence of connected objects have changed the agricultural area. In this new digital age, the development of artificial intelligence, particularly deep learning, has allowed for acceleration and improvement in the processing of collected data. To highlight the evolution and advances observed in deep learning in agriculture, we conducted a bibliometric study on more than 400 recent research studies. The analyses carried out on recent research works suggest that deep learning is widely involved in the digitization of agriculture areas with high accuracy exceeding the standard image processing techniques. Most of the works focus on crop classification problems, weed, and pest identification. Their methods are mainly based on convolutional neural network architecture. From the cases study, we have identified three key challenges that are essential in the deep learning methods applied in agriculture: (i) the need to consider the perception of the domain actors, their appropriation or interaction with the existing tools; (ii) the requirement to perform statistical tests to analyze the performance of the classifiers resulting from the learning process; and (iii) the need to perform statistical cross-validations with the training data. In the end, we summarized the agricultural data processing process consisting of several parts, for a better consideration of the expectations resulting from the challenges addressed. We consider that this study can serve as a guideline of research for the scientist and practician in the application of deep learning methodology in agriculture.
Remote sensing based on Remote Piloted Aircraft Systems (RPAS) has proved valuable for monitoring agronomic parameters in precision agriculture. This research aimed to develop predictive models based ...on machine learning to estimate indirect nitrogen levels (Narea) and grain yield in irrigated rice. During the five phenological stages of cultivation, a Sequoia® camera aboard the Phantom 4® Pro platform acquired the multispectral images. In addition to the spectral bands, 11 vegetation indices were taken as predictors of the response variables (Narea and grain yield). Spearman's correlation coefficient (p) analyzed the ideal monitoring window and selected the model variables. The Multi-Layer Perceptron (MLP) algorithm adjusted the predictive models that had their performance evaluated in training and testing. The results obtained by the Spearman correlation indicate that the ideal window for monitoring rice by RPAS, for both response variables, occurs at the beginning of the reproduction phase (R1). MLP generated a more accurate model for Narea, demonstrated by Pearson's correlation between predicted and observed values (0.82 and 0.71) and mean absolute error (MAE) of 9.47 and 10.89. Grain yield models show good MLP at all stages and excellent accuracy. In this way, our results reinforce the excellent efficiency of the combination of remote sensing via RPAS and machine learning in applications aimed at precision agriculture, serving as a useful tool for managing production and evaluating grain yield in irrigated rice fields.
The sustainable management of water resources is one of the most important topics to face future climate change and food security. Many countries facing a serious water crisis, due to both natural ...and artificial causes. The efficient use of water in agriculture is one of the most significant agricultural challenges that modern technologies. These last are considered powerful management instruments able to help farmers achieve the best efficiency in irrigation water use and to increase their incomes by obtaining the highest possible crop yield. In this context, within the project "An advanced low cost system for farm irrigation support-LCIS" (a joint Italian Israeli R&D project), a fully transferable Decision Support Systems (DSS) for irrigation support, based on three different methodologies representative of the state of the art in irrigation management tools (W-Tens, in situ soil sensor; IRRISAT®, remote sensing; W-Mod, simulation modelling of water balance in the soil-plant and atmosphere system), has been developed. These three LCIS-DSS tools have been evaluated, in terms of their ability to support the farmer in irrigation management, in a real applicative case study in Italy and Israel. The main challenge of a new DSS for irrigation is attributed to the uncertain factors during the growing season such as weather uncertainty, and crop monitoring platform. For encounter this challenge, we developed during two years the LCIS, a web-based real-time DSS for irrigation scheduling using low-cost imaging spectroscopy for state estimation of the agriculture system and probabilistic short- and medium-term climate forecasts. While the majority of the existing DSS models are incorporated directly into the optimization framework, we propose to integrate continuous feedback from the field (e.g., soil moisture, crop water-stress, plant stage, LAI, and biomass) estimated based on remote sensing information. These field data will be collected by the point-based spectrometer and hyperspectral imaging system. Then a low-cost camera will be designed for specific spectral/spatial parameters (bound to the required feedbacks). The main objectives were: developing real-time Decision Support System (DSS) for optimal irrigation scheduling at farm scale for crop yield improvement, reducing irrigation cost, and water saving; developing a low-cost imaging spectroscopy framework to support the irrigation scheduling DSS above and facilitates its use in countries/places where expensive imaging spectroscopy is not available; examining the developed framework in real-life application, the framework will be calibrated evaluated using high resolution devices and tested using a low-cost system in Israel and Italy farms.
The adoption of new technologies, such as unmanned aerial vehicles (UAVs), image processing, and machine learning, is disrupting traditional concepts in agriculture, with a new range of possibilities ...opening in its fields of research. Plant density is one of the most important corn (Zea mays L.) yield factors, yet its precise measurement after the emergence of plants is impractical in large-scale production fields due to the amount of labor required. This letter aims to develop techniques that enable corn plant counting and the automation of this process through deep learning and computational vision, using images of several corn crops obtained using a low-cost unmanned aerial vehicle (UAV) platform assembled with an RGB sensor.
Big data with its vast volume and complexity is increasingly concerned, developed and used for all professions and trades. Remote sensing, as one of the sources for big data, is generating ...earth-observation data and analysis results daily from the platforms of satellites, manned/unmanned aircrafts, and ground-based structures. Agricultural remote sensing is one of the backbone technologies for precision agriculture, which considers within-field variability for site-specific management instead of uniform management as in traditional agriculture. The key of agricultural remote sensing is, with global positioning data and geographic information, to produce spatially-varied data for subsequent precision agricultural operations. Agricultural remote sensing data, as general remote sensing data, have all characteristics of big data. The acquisition, processing, storage, analysis and visualization of agricultural remote sensing big data are critical to the success of precision agriculture. This paper overviews available remote sensing data resources, recent development of technologies for remote sensing big data management, and remote sensing data processing and management for precision agriculture. A five-layer-fifteenlevel (FLFL) satellite remote sensing data management structure is described and adapted to create a more appropriate four-layer-twelve-level (FLTL) remote sensing data management structure for management and applications of agricultural remote sensing big data for precision agriculture where the sensors are typically on high-resolution satellites, manned aircrafts, unmanned aerial vehicles and ground-based structures. The FLTL structure is the management and application framework of agricultural remote sensing big data for precision agriculture and local farm studies, which outlooks the future coordination of remote sensing big data management and applications at local regional and farm scale.
Climate change has introduced significant challenges that can affect multiple sectors, including the agricultural one. In particular, according to the Food and Agriculture Organization of the United ...Nations (FAO) and the International Telecommunication Union (ITU), the world population has to find new solutions to increase the food production by 70% by 2050. The answer to this crucial challenge is the suitable adoption and utilisation of the Information and Communications Technology (ICT) services, offering capabilities that can increase the productivity of the agrochemical products, such as pesticides and fertilisers and at the same time, they should minimise the functional cost. More detailed, the advent of the Internet of Things (IoT) and specifically, the rapid evolution of the Unmanned Aerial Vehicles (UAVs) and Wireless Sensor Networks (WSNs) can lead to valuable and at the same time economic Precision Agriculture (PA) applications, such as aerial crop monitoring and smart spraying tasks. In this paper, we provide a survey regarding the potential use of UAVs in PA, focusing on 20 relevant applications. More specifically, first, we provide a detailed overview of PA, by describing its various aspects and technologies, such as soil mapping and production mapping as well as the role of the Global Positioning Systems (GPS) and Geographical Information Systems (GIS). Then, we discriminate and analyse the various types of UAVs based on their technical characteristics and payload. Finally, we investigate in detail 20 UAV applications that are devoted to either aerial crop monitoring processes or spraying tasks. For each application, we examine the methodology adopted, the proposed UAV architecture, the UAV type, as well as the UAV technical characteristics and payload.