A Comprehensive Approach to Assessing Yield Map Quality in Smart Agriculture: Void Detection and Spatial Error Mapping

The chapter deals with techniques used for yield monitoring and mapping in precision agriculture. Yield maps are one of the most valuable sources of spatial data for precision agriculture. In developing these maps, it is essential to remove the data points that do not accurately represent the yield at a corresponding location. Map averaging or smoothing is usually done to aid data interpretation. A long yield history is essential to avoid drawing conclusions that are affected by the weather or other unpredictable factors during a particular year. Typically, at least 5 years of yield maps are desired. Processed yield maps can be used to investigate factors affecting the yield or to prescribe variable rate applications of agricultural inputs according to spatially variable yield goals (yield potential). Producers interested in precision farming should, however, always evaluate different management approaches to identify those that provide the greatest benefit at a particular site.

In robotics and computer vision, point set registration is necessary in many tasks, for example in estimating the motion of a sensor/sensors between subsequent scans containing point/feature sets. Currently, the Iterated Closest Point (ICP) method and its variants have been presented as possible solutions to this problem. However most of these methods lack robustness when random spatial and detection errors are present. This is because ICP methods typically use an L2 metric as part of their optimization criteria, which is unable to penalize cardinality errors. Therefore, this article presents a registration technique based on the multi-object Optimal Sub-Pattern Assignment (OSPA) and Cardinalized Optimal Linear Assignment (COLA) metrics, which penalize data differences based on both cardinality and spatial errors. This allows scan registration to take place in the presence of both inter-scan translation and orientation as well as detection errors.

One of the basic tools used in precision agriculture technology is yield monitoring and mapping. Yield maps are used to monitor the efficiency of applied inputs, to assess the variability of field and have potential to be used in farm records and farm management software. The paper deals with comparison of yield maps with information on yield obtained from hand sampling. Analyses are based on five-year data from one field with spring barley, oil seed rape, winter wheat and maize crop rotation. Results show that the correlation coefficient across the time period reached a value of 0.89 (p <0.05), which means that the yield maps show the yield trend of the field. However, looking at the data in more detail and comparing the pairs of data for selected (discrete) monitoring points, the error of estimation was calculated. This error showed that the yield monitor underestimated or overestimated the yield in average by 25 %. Therefore, the data cannot be used to evaluate the absolute yield at selected place of the field.

In the health care environment, a huge volume of data is produced on a daily basis. However, the processes of collecting, storing, sharing, analyzing, and reporting health data usually face with numerous challenges that lead to producing incomplete, inaccurate, and untimely data. As a result, data quality issues have received more attention than before. The purpose of this article is to provide an insight into the data quality definitions, dimensions, and assessment methodologies. In this article, a scoping literature review approach was used to describe and summarize the main concepts related to data quality and data quality assessment methodologies. Search terms were selected to find the relevant articles published between January 1, 2012 and September 31, 2022. The retrieved articles were then reviewed and the results were reported narratively. In total, 23 papers were included in the study. According to the results, data quality dimensions were various and different methodologies were used to assess them. Most studies used quantitative methods to measure data quality dimensions either in paper-based or computer-based medical records. Only two studies investigated respondents' opinions about data quality. In health care, high-quality data not only are important for patient care, but also are vital for improving quality of health care services and better decision making. Therefore, using technical and nontechnical solutions as well as constant assessment and supervision is suggested to improve data quality.

Accurate, timely, and non-destructive early crop yield prediction at the field scale is essential in addressing changing crop production challenges and mitigating impacts of climate variability. Unmanned aerial vehicles (UAVs) are increasingly popular in recent years for agricultural remote sensing applications such as crop yield forecasting and precision agriculture (PA). The objective of this study was to evaluate the performance of a low-cost UAV-based remote sensing technology for Bambara groundnut yield prediction. A multirotor UAV equipped with a near-infrared sensitive consumer-grade digital camera was used to collect image data during the 2018 growing season (April to August). Flight missions were carried out six times during critical phenological stages of the life-cycle of the monitored crop. Yield was recorded at harvest. Four vegetation indices (VIs) namely normalized difference vegetation index (NDVI), enhanced vegetation index 2 (EVI2), green normalized difference vegetation index (GNDVI), and simple ratio (SR) generated from the Red-Green-Near Infrared bands were calculated using the georeferenced orthomosaic UAV images. Pearson’s product-moment correlation coefficient (r) and Bland–Altman testing showed a significant agreement between remotely and proximally sensed VIs. Significant and positive correlations were found between the four VIs and yield, with the strongest relationship observed between SR and yield at podfilling stage (r = 0.81, P < 0.01). Multi-temporal accumulative VIs improved yield prediction significantly with the best index being ∑SR and the best interval being from podfilling to maturity (r = 0.88, P < 0.01). The accumulated ∑SR from podfilling to maturity resulted in higher prediction accuracy with a coefficient of determination (R 2) of 0.71, root mean square error (RMSE) of 0.20 and mean absolute percentage error (MAPE) of 14.2% than SR spectral index at a single stage (R 2 = 0.68, RMSE = 0.24, MAPE = 15.1%). Finally, a yield map was generated using the model developed, to better understand the within-field spatial variations of yield for future site-specific or variable-rate application operations.

Within precision agriculture, yield mapping is important in the evaluation of crop management and delineation of management zones. It can also be used to assess within-field yield potential, in order to guide different precision agriculture practices. However, some farmers do not have a yield monitoring system, and some who do may obtain incomplete or erroneous yield data. This study examined the accuracy with which winter wheat (Triticum aestivum L.) yield could be mapped in 18 fields in southern Sweden using a simple empirical relationship between Sentinel-2 (ESA, Paris, France) data, vegetation index (VI) maps and combined harvester data collected in nearby fields. The results showed that a decrease in map resolution to 40 m reduced the error in the yield maps obtained. Normalised difference water index (NDWI) was the most efficient VI, while a combination of satellite data from earlier and later plant development (booting and milk development stages) performed slightly better than data for other development stages and combinations. The best-performing model at a within-field scale (40-m resolution) had an average mean absolute error (MAE) of 0.40 tonnes ha−1 in a leave-one-field-out cross validation. When the prediction model at field-means scale was applied on 69 farms in a 1055 km2 area, MAE was 0.75 tonnes ha−1 when comparing predictions with mean yields reported by farmers in a phone survey. Therefore, if adequate combined harvester and/or mean yield data are available, a modelling framework that translates satellite imagery into yield maps on-the-fly could be made available for different stakeholders via decision support systems for precision agriculture.

The proliferation of volunteered geographic information (VGI), such as OpenStreetMap (OSM) enabled by technological advancements, has led to large volumes of user-generated geographical content. While this data is becoming widely used, the understanding of the quality characteristics of such data is still largely unexplored. An open research question is the relationship between demographic indicators and VGI quality. While earlier studies have suggested a potential relationship between VGI quality and population density or socio-economic characteristics of an area, such relationships have not been rigorously explored, and mainly remained qualitative in nature. This paper addresses this gap by quantifying the relationship between demographic properties of a given area and the quality of VGI contributions. We study specifically the demographic characteristics of the mapped area and its relation to two dimensions of spatial data quality, namely positional accuracy and completeness of the corresponding VGI contributions with respect to OSM using the Denver (Colorado, US) area as a case study. We use non-spatial and spatial analysis techniques to identify potential associations among demographics data and the distribution of positional and completeness errors found within VGI data. Generally, the results of our study show a lack of statistically significant support for the assumption that demographic properties affect the positional accuracy or completeness of VGI. While this research is focused on a specific area, our results showcase the complex nature of the relationship between VGI quality and demographics, and highlights the need for a better understanding of it. By doing so, we add to the debate of how demographics impact on the quality of VGI data and lays the foundation to further work.

Abstract. The availability and accessibility of remote sensing (RS) data, cloud processing platforms and provided information products and services has increased the size and diversity of the RS user community. This development also generates a need for validation approaches to assess data quality. Validation approaches employ quality criteria in their assessment. Data Quality (DQ) dimensions as the basis for quality criteria have been deeply investigated in the database area and in the remote sensing domain. Several standards exist within the RS domain but a general classification – established for databases – has been adapted only recently. For an easier identification of research opportunities, a better understanding is required how quality criteria are employed in the RS lifecycle. Therefore, this research investigates how quality criteria support decisions that guide the RS lifecycle and how they relate to the measured DQ dimensions. Subsequently follows an overview of the relevant standards in the RS domain that is matched to the RS lifecycle. Conclusively, the required research needs are identified that would enable a complete understanding of the interrelationships between the RS lifecycle, the data sources and the DQ dimensions, an understanding that would be very valuable for designing validation approaches in RS.

Este trabalho foi realizado em duas lavouras monitoradas intensivamente como áreas- piloto de agricultura de precisão. Vários dados estão sendo obtidos como mapeamento de produtividade, levantamentos de propriedades físicas e químicas do solo, pragas, doenças e plantas invasoras, bem como fotografias aéreas coloridas no formato 35 mm. As fotografias receberam orientação por bandeiras georreferenciadas em solo com DGPS para a correção geométrica das imagens e, após selecionadas, foram digitalizadas por meio de scanner. Foram, então, analisados os coeficientes de determinação entre o valor digital das imagens e a produtividade. Os coeficientes de determinação para as duas áreas, em todos os períodos analisados, apresentaram valores baixos, não havendo correspondência entre os valores digitais das imagens e as produtividades.

Precision agriculture leverages data science and technology to optimize farming practices, enhance crop yields, and promote sustainability. This review examines how data-driven approaches are revolutionizing agriculture through improved decision-making, resource efficiency, and environmental stewardship. Key technologies enabling precision agriculture are discussed, including remote sensing, IoT sensors, AI/machine learning, and farm management information systems. The paper explores applications such as variable rate technology, yield mapping, and predictive analytics. Challenges related to data management, interoperability, and adoption barriers are analyzed. The review concludes that precision agriculture, powered by data science, offers significant potential to address food security and sustainability challenges, but requires continued research and interdisciplinary collaboration to realize its full benefits.

The processes by which plant spatial patterns are formed, and the effects of those patterns on plant community dynamics, remain important areas of research in plant ecology. Plant spatial pattern formation has been linked to many ecological processes that act to structure plant communities at different spatiotemporal scales. Past studies of pattern formation are common, but recent methodological advances in data collection and analysis have permitted researchers to conduct more advanced observational studies of pattern formation in space and time. While studies of the effects of plant spatial patterns were formally rare, they have increased in the last decade as new types of experiments and analysis have been developed to better understand the myriad effects of plant patterns on community dynamics. My dissertation research examined both the causes and consequences of plant spatial patterns in the context of natural and experimental Great Basin semi-arid plant communities. In both cases, I implemented novel methodologies for data collection, experimental design, and data analysis in an attempt to address current gaps in knowledge related to the processes by which plant spatial patterns are formed, as well as the effect of plant spatial patterns on community dynamics. The results inform both basic and applied plant ecology, and set the stage for further research on the causes and consequences of plant spatial patterns in semi-arid plant communities.

A company's value proposition is established by the distinctive benefits and values it offers to its clients. Site-specific crop management (SSCM) and precision agriculture (PA) are farming management techniques that use technology to monitor and evaluate certain areas and crops. Between 2023 and 2030, the market for precision agriculture is anticipated to increase at a CAGR of 12.6%, reaching $15.6 billion. Precision farm planning, field maps, crop scouting, yield maps, and the estimation of input quantities are driving factors in this growth, along with the Internet of Things and advanced analytics. A company's commitment to influencing the attitudes, beliefs, and behavior of its target market is stated in its value proposition. The goal of the study was to address agricultural issues and increase productivity and profitability for banana farmers in the Anand and Umreth Talukas. Educate stakeholders, decision-makers, and service providers on how to support precision farming techniques. The study, conducted in Anand and Umreth Taluka, Gujarat, involved 50 banana growers with over 2 ha of land, using a descriptive design and semi-structured survey. Formulating a customer value proposition for identifying the problems faced by banana growers will help in understanding the current issues and areas of improvement within the agricultural sector. The findings of this research were contributing to the knowledge and understanding of precision farming in Anand and Umreth Talukas. Customers place a premium on product quality, the accessibility of the sales staff, and price, while farmers must deal with issues including disease, weather, nutrition, insect pests, and irrigation. Irrigation was viewed as less significant than weather and illness, which were found the major problems in the study area. Decision-making in agriculture depends heavily on weather forecasts and practices. A substantial effort was needed to improve agricultural practices because of the influence of climate change, input market accessibility, and remote farm access.

Despite the increasing availability of biodiversity data, determing the quality of data and informing would-be data consumers and users remains a significant issue. In order for data users and data owners to perform a satisfactory assessment and management of data fitness for use, they require a Data Quality (DQ) report, which presents a set of relevant DQ measures, validations, and amendments assigned to data. Determining the meaning of "fitness for use" is essential to best manage and assess DQ. To tackle the problem, the TDWG Biodiversity Data Quality (BDQ) - Interest Group (IG) (https://github.com/tdwg/bdq) has proposed a conceptual framework that defines the necessary components to describe Data DQ needs, DQ solutions, and DQ reports (Fig. 1). It supports, in a global and collaborative environment, a consistent description of: (1) the meaning of data fitness for use in specific contexts, using the concept of a DQ profile; (2) DQ solutions, using the concepts of specifications and mechanisms; and (3) the status of quality of data according to a DQ profile, using the concept of a DQ report (Veiga 2016, Veiga et al. 2017). Based on this this conceptual framework, we implemented a prototype of a Fitness for Use Backbone (FFUB) as a Node.js module (https://nodejs.org/api/modules.html) for registering and retrieving instances of the framework concepts. This prototype was built using Node.js, an asynchronous event-driven JavaScript runtime, which uses a non-blocking I/O model that makes it lightweight and efficient to build scalable network applications (https://nodejs.org). We registered our module in the npm package manager (https://www.npmjs.com) in order to facilitate its reuse and we made our source code available in GitHub (https://github.com) in order to foster collaborative development. To test the module, we developed a simple mechanism for measuring, validating and amending the quality of datasets and records, called BDQ-Toolkit, available in the FFUB module. The source code of the FFUB module can be found at https://github.com/BioComp-USP/ffub. Installing and using the module requires Node.js version 6 or higher. Instructions for installing and using the FFUB module can be found at https://www.npmjs.com/package/ffub (Veiga and Saraiva 2017). Using the FFUB module we defined a simple DQ profile describing the meaning of data fitness for use in a specific context by registering a hypothetical use case. Then, we registered a set of valuable information elements for the context of the use case. For measuring the quality of each valuable information elements, we registered a set of DQ dimensions. To validate if the DQ measures are good enough, a set of DQ criteria was defined and registered. Lastly, a set of DQ enhancements for amending the quality in the use case context was also defined and registered. In order to describe the DQ solution used to meet those DQ needs, we registered the BDQ-Toolkit mechanism and all the specifications implemented by it. Using these specifications and mechanism, we generated and assigned to a dataset and its records a set of DQ assertions, according to the DQ dimensions, criteria and enhancements defined in the DQ profile. Based on those assertions we can build DQ reports by composing all the assertions assigned to the dataset or to a specific record. This DQ report describes the status of DQ of a dataset or record according to the context of the DQ profile. This module provides an interface to use the proposed conceptual framework, which allows others to register instances of its concepts. Future work will include creating a RESTful API using sophisticated methods of data retrieval.

Precision agriculture aims at adjusting and fine-tuning land and crop management to the needs of plants within heterogeneous fields. Production aspects have to be balanced against environmental threshold values and modern information technology has made it possible to devise operational field systems. A reactive approach is described, using yield maps and sensors. A proactive approach uses simulation modelling of plant growth and solute fluxes to predict optimal timing of management practices. Precision agriculture, combining both approaches, is seen as making a major contribution towards the development of sustainable agricultural production systems.

Yield mapping visualizes yield rate per geological distribution. It is frequently used as a baseline metric to measure yield efficiency in precision farming. A major challenge in mapping yield for specialty crops is how to collect accurate yield data without incurring substantial overhead to a farming operation. We design a yield efficiency analysis system that uses a cloud-based computing platform to acquire and analyze yield data. By reusing labor data collected by a cloud-based labor monitoring system that we developed earlier, our system calculates yield data from labor data, and computes yield map in real time and without the overhead for data acquisition. A distinctive feature of our approach is the introduction of a customizable yield distribution function that quantifies the probability of geographic distribution of fruits weighted at a Labor Monitoring Device. Practitioners may define yield distribution functions based on operational characteristics of an orchard, enabling our system adaptive for a variety of orchards with different harvesting operations and canopy architecture. Using a multi-tenancy software architecture, our system can support multiple orchards concurrently with improved scalability and data privacy. Our system has been deployed and tested on Amazon Web Services (AWS).