Automatic arable land detection with supervised machine learning

Text mining is a special case of data mining which explore unstructured or semi-structured text documents, to establish valuable patterns and rules that indicate trends and significant features about specific topics. Text mining has been in pattern recognition, predictive studies, sentiment analysis and statistical theories in many areas of research, medicine, financial analysis, social life analysis, and business intelligence. Text mining uses concept of natural language processing and machine learning. Machine learning algorithms have been used and reported to give great results, but their performance of machine learning algorithms is affected by factors such as dataset domain, number of classes, length of the corpus, and feature selection techniques used. Redundant attribute affects the performance of the classification algorithm, but this can be reduced by using different feature selection techniques and dimensionality reduction techniques. Feature selection is a data preprocessing step that chooses a subset of input variable while eliminating features with little or no predictive information. Feature selection techniques are Information gain, Term Frequency, Term Frequency-Inverse document frequency, Mutual Information, and Chi-Square, which can use a filters, wrappers, or embedded approaches. To get the most value from machine learning, pairing the best algorithms with the right tools and processes is necessary. Little research has been done on the effect of feature selection techniques on classification accuracy for pairing of these algorithms with the best feature selection techniques for optimal results. In this research, a text classification experiment was conducted using incident management dataset, where incidents were classified into their resolver groups. Support vector machine (SVM), K-Nearest Neighbors (KNN), Naïve Bayes (NB) and Decision tree (DT) machine learning algorithms were examined. Filtering approach was used on the feature selection techniques, with different ranking indices applied for optimal feature set and classification accuracy results analyzed. The classification accuracy results obtained using TF were, 88% for SVM, 70% for NB, 79% for Decision tree, and KNN had 55%, while Boolean registered 90%, 83%, 82% and 75%, for SVM, NB, DT, and KNN respectively. TF-IDF, had 91%, 83%, 76%, and 56% for SVM, NB, DT, and KNN respectively. The results showed that algorithm performance is affected by feature selection technique applied. SVM performed best, followed by DT, KNN and finally NB. In conclusion, presence of noisy data leads to poor learning performance and increases the computational time. The classifiers performed differently depending on the feature selection technique applied. For optimal results, the classifier that performed best together with the feature selection technique with the best feature subset should be applied for all types of data for accurate classification performance. Keywords: Text Classification, Supervised Machine Learning, Feature Selection DOI : 10.7176/JIEA/9-3-06 Publication date :May 31 st 2019

Precision agriculture or operational agriculture is a dynamically developing field of agricultural science, which is based on geoinformatics. Agrometeorological remote sensing contributes through processing and analysis of high resolution satellite images to decision support at field level. In this paper, in HYDROSENSE project, the classification of organic matter zones is presented aiming at the assessment of water and fertilizer operational needs per zone for cotton crops in Thessaly during the phenological cycle. Two pan-sharpened satellite images WorldView-2 (0.5 m) of the region are used, one before planting and the other at the maximum plant cover, as well as one pan-sharpened reference satellite image (2007) IKONOS-2 (1 m). The methodological processing approach includes image filtering and preprocessing, as well as processing, which involves principal component analysis and clustering leading to the production of thematic maps. These maps are combined with mapping through geostatistical analysis of weekly periodic field measurements in three selected cotton fields referring to NDVI, Red/Red edge, NIR/Red and the development of a mini GIS. The results of this combined analysis lead to organic matter zones of the whole region for decision support in precision agriculture.

Scale abbreviation is a crucial task for researchers aiming to reduce response burden and optimize data collection when using self-report instruments such as online surveys and questionnaires. Among various data-driven strategies available for scale abbreviation, supervised machine learning (SML) algorithms have emerged as a prominent approach due to their accuracy in predicting total scores from the original instrument. However, previous studies offer limited insights into how SML-abbreviated scales can be evaluated using both SML and psychometric metrics across different feature selection techniques. To address this gap, the current study aims to evaluate the effectiveness of seven feature selection methods: item-total-correlation-based filters (ITC), Minimum-Redundancy-Maximum-Relevance (MRMR), Lasso, Sequential Forward Selection (SFS), Sequential Backward Selection (SBS), Genetic Algorithms (GA), and Non-dominated Sorting Genetic Algorithms-II (NSGA-II), all used in conjunction with SML. Additionally, the psychometric properties of these SML methods are compared with two non-SML approaches. Using simulated datasets varying in sample size, model error, and factorial correlations, the study examines predictive accuracy, reliability, and the ability to recover both inter-subscale correlations and external criterion correlations. The findings indicate that no single method consistently excels across all conditions, with specific feature selection techniques performing better under certain circumstances. Key insights are provided to guide researchers in selecting appropriate feature selection methods based on their specific dataset characteristics and goals.

: The criteria for landing zones (LZs) and drop zones (DZs), also known as austere entry surfaces, are extensive and varied. They range from very specific guidance on required geometry to more general guidance on required bearing strength of unprepared surfaces, such as soil or ice, and the smoothness of those surfaces. Current practice for siting LZs and DZs includes site surveys by trained personnel, often in hostile environments. Additionally, with the continued advancement of image analysis, it may be possible to identify potential LZ and DZ sites remotely and thus to reduce the need to expose personnel to dangerous conditions. This review intends to summarize existing Federal, Department of Defense, and other criteria for unsurfaced, unimproved LZs and DZs. The purpose of the summary is to consolidate criteria so that the criteria may be considered in the process of developing and refining methods to remotely locate and assess potential LZs and DZs by using satellite imagery.

The fusion of unmanned aerial system (UAS) and satellite imagery has emerged as a pivotal strategy in advancing precision agriculture. This review explores the significance of integrating high-resolution UAS and satellite imagery via pixel-based, feature-based, and decision-based fusion methods. The study investigates optimization techniques, spectral synergy, temporal strategies, and challenges in data fusion, presenting transformative insights such as enhanced biomass estimation through UAS-satellite synergy, improved nitrogen stress detection in maize, and refined crop type mapping using multi-temporal fusion. The combined spectral information from UAS and satellite sources confirms instrumental in crop monitoring and biomass estimation. Temporal optimization strategies consider factors such as crop phenology, spatial resolution, and budget constraints, offering effective and continuous monitoring solutions. The review systematically addresses challenges in spatial and temporal resolutions, radiometric calibration, data synchronization, and processing techniques, providing practical solutions. Integrated UAS and satellite data impact precision agriculture, contributing to improved resolution, monitoring capabilities, resource allocation, and crop performance evaluation. A comparative analysis underscores the superiority of combined data, particularly for specific crops and scenarios. Researchers exhibit a preference for pixel-based fusion methods, aligning fusion goals with specific needs. The findings contribute to the evolving landscape of precision agriculture, suggesting avenues for future research and reinforcing the field’s dynamism and relevance. Future works should delve into advanced fusion methodologies, incorporating machine learning algorithms, and conduct cross-crop application studies to broaden applicability and tailor insights for specific crops.

This cumulative thesis addresses two key challenges facing modern arable farming in Germany in the 21st century. The first challenge considered is the agricultural land market. The ongoing reduction in the limited production factor of land and the sharp price increases on the purchase and rental market for agricultural land are leading to an ongoing social, political and scientific debate about causes, effects and the need for political intervention. The scarcity of land requires an increase in productivity from a sectoral perspective and an increase in the profitability of the land under cultivation from a business management perspective. Additionally, sustainability and resource efficiency are playing a considerably increasing role in arable farming. By adopting precision agriculture technologies, farmers can increase farm productivity by improving yields while reducing input use and external environmental impacts. Therefore, the adoption of precision agriculture technologies is considered an important goal and current challenge in arable farming. Drones are one of the newest technologies belonging to precision agriculture, and many potential applications are promised due to their multifunctionality. Nevertheless, so far drones are less used in arable farming than expected and very little is known about the adoption process of drones. The adoption of precision agriculture technologies, and in this case specifically the case of drones, is therefore considered as the second key challenge in arable farming in the cumulative thesis. The first paper studies the status quo regarding price drivers on European farmland rental markets according to current literature and offers primary survey results of German farmers’ perceptions regarding those identified price drivers. Results show that "policy/CAP", "bioenergy", "climate change" as well as "market prices/competition" are identified by the primary literature as central price drivers on the European farmland rental markets and that the surveyed German farmers perceive these four price drivers differently from the literature regarding their relevance. The second paper studies the effect of restricted tendering in farmland auctions as a widely used policy intervention tool on the agricultural land market utilizing Propensity Score Matching (PSM) and auction theory. It is demonstrated that restricted tendering in land market auctions reduces the average number of bidders but does not fulfill the ultimate purpose of lower prices for structurally disadvantaged groups of bidders, as it leads to higher purchase prices on average. In the third paper, key factors influencing the adoption of drones are studied with a modified trans-theoretical model of adoption (TTMA). The focus of this fundamental research is mainly on sociodemographic farm and farmer characteristics. Results show that, among other factors, farmers' age, gender, and technology literacy, as well as farm size, influence the adoption process of drones in arable farming. The fourth paper extends the scope of research towards the latent factors influencing the adoption process of drones in arable farming based on an extended Technology Acceptance Model (TAM). It is shown that both raising farmers' awareness of farm-specific applications of drones and confidence in using a drone can increase farmers' intention to use a drone. The results are primarily of interest to agricultural policymakers who are involved in the active debate on agricultural land market interventions as well as those who wish to politically promote the dissemination of PAT. Furthermore, the results are of interest to farmers, (potential) buyers in the farmland market and agricultural expansion services. Developers and providers of drones and farm equipment that integrates drone technology could also benefit from this research. Each of the papers contributes to its particular body of literature and shows potential directions for future research.

There has been a recent surge in the number of studies that aim to model crop yield using data-driven approaches. This has largely come about due to the increasing amounts of remote sensing (e.g. satellite imagery) and precision agriculture data available (e.g. high-resolution crop yield monitor data), as well as the abundance of machine learning modelling approaches. However, there are several common issues in published studies in the field of precision agriculture (PA) that must be addressed. This includes the terminology used in relation to crop yield modelling, predicting, forecasting, and interpolating, as well as the way that models are calibrated and validated. As a typical example, many studies will take a crop yield map or several plots within a field from a single season, build a model with satellite or Unmanned Aerial Vehicle (UAV) imagery, validate using data-splitting or some kind of cross-validation (e.g. k-fold), and say that it is a ‘prediction’ or ‘forecast’ of crop yield. However, this poses a problem as the approach is not testing the forecasting ability of the model, as it is built on the same season that it is then validating with, thus giving a substantial overestimation of the value for decision-making, such as an application of fertiliser in-season. This is an all-too-common flaw in the logic construct of many published studies. Moving forward, it is essential that clear definitions and guidelines for data-driven yield modelling and validation are outlined so that there is a greater connection between the goal of the study, and the actual study outputs/outcomes. To demonstrate this, the current study uses a case study dataset from a collection of large neighbouring farms in New South Wales, Australia. The dataset includes 160 yield maps of winter wheat (Triticum aestivum) covering 26,400 hectares over a 10-year period (2014–2023). Machine learning crop yield models are built at 30 m spatial resolution with a suite of predictor data layers that relate to crop yield. This includes datasets that represent soil variation, terrain, weather, and satellite imagery of the crop. Predictions are made at both the within-field (30 m), and field resolution. Crop yield predictions are useful for an array of applications, so four different experiments were set up to reflect different scenarios. This included Experiment 1: forecasting yield mid-season (e.g. for mid-season fertilisation), Experiment 2: forecasting yield late-season (e.g. for late-season logistics/forward selling), Experiment 3: predicting yield in a previous season for a field with no yield data in a season, and Experiment 4: predicting yield in a previous season for a field with some yield data (e.g. two combine harvesters, but only one was fitted with a yield monitor). This study showcases how different model calibration and validation approaches clearly impact prediction quality, and therefore how they should be interpreted in data-driven crop yield modelling studies. This is key for ensuring that the wealth of data-driven crop yield modelling studies not only contribute to the science, but also deliver actual value to growers, industry, and governments.

The integration of multimodal data and artificial intelligence (AI) in precision agriculture has the potential to significantly improve crop monitoring, management, and overall agricultural productivity. Precision agriculture is advancing rapidly by utilizing multimodal data and intelligent system design. These help to improve decision-making and increase farming efficiency. The main challenges are the fusion of data, introducing AI-powered analytics, and human-computer interaction (HCI) in the field of smart agricultural services. To address the challenges, we investigate how to merge various forms of data. Also, we studied innovative applications to use multimodal data and an intelligent system design to improve crop monitoring and management. This research shows a novel aspect to utilize and explains the difficulties of working with a variety of data sources, such as satellite images, sensor data, weather reports, and farmer inputs, to design an intelligent system. In addition, this research examines how advanced data fusion techniques bring these disparate data types together to provide accurate, real-time insights that help optimize farming practices. AI analytics enable intelligent decision-making and timely alerts, resulting in improved agricultural practices using an advanced predictive machine learning (ML) model. This study adds to the expanding body of knowledge on precision agriculture by introducing novel methodology and practical applications, opening the door for more sustainable and intelligent farming systems.

Precision agriculture is the process that uses information and communication technology for farming and cultivation to improve overall productivity, efficient utilization of resources. Soil prediction is one of the primary phases in precision agriculture, resulting in good quality crops. In general, farmers perform the soil prediction manually. However, the efficiency of soil prediction may be enhanced by the use of current digital technologies. One effective way to automate soil prediction is image processing techniques in which soil images may be analyzed to determine the soil. This paper presents an efficient image analysis technique to predict the soil. For the same, a robust feature selection technique has been incorporated in the image analysis of soil images. The developed feature selection technique uses a new oscillating spider monkey optimization algorithm (OSMO) for the selection of features that are relevant and non-redundant. The new oscillating spider monkey optimization algorithm uses an oscillating perturbation rate to increase its precision and convergence behavior. A set of standard benchmark functions was deployed to visualize the performance of the new optimization technique (OSMO), and results were compared based on mean and standard deviation. Furthermore, the soil prediction approach is validated on a soil dataset, having seven categories. The proposed feature selection method selects the 41% relevant features, which provide the highest accuracy of 82.25% with 2.85% increase.

Two different methods of Bayesian segmentation algorithm were used with different band combinations. Sequential Maximum a Posteriori (SMAP) is a Bayesian image segmentation algorithm which unlike the traditional Maximum likelihood (ML) classification attempts to improve accuracy by taking contextual information into account, rather than classifying pixels separately. Landsat 7 ETM+ data with Path/Row 186-26, dated 30 September 2000 for a mountainous terrain at the Polish - Ukrainian border is acquired. In order to study the role of thermal band with these methods, two data sets with and without the thermal band were used. Nine band combinations including ETM+ and Principal Component (PC) data were selected based on the highest value of Optimum Index Factor (OIF). Using visual and digital analysis, field observation data and auxiliary map data like CORINE land cover, 14 land cover classes are identified. Spectral signatures were derived for every land cover. Spectral signatures as well as feature space analysis were used for detailed analysis of efficiency of the reflective and thermal bands. The result shows that SMAP as the superior method can improve Kappa values compared with ML algorithm for all band combinations with on average 17%. Using all 7 bands both SMAP and ML classifications algorithm achieved the highest Kappa accuracy of 80.37 % and 64.36 % respectively. Eliminating the thermal band decreased the Kappa values by about 8% for both algorithms. The band combination including PC1, 2, 3, and 4 (PCA calculated for all 7 bands) produced the same Kappa as bands 3, 4, 5 and 6. The Kappa value for band combination 3, 4, 5 and 6 was also about 4% higher than using 6 bands without the thermal band for both algorithms. Contextual classification algorithm like SMAP can significantly improve classification results. The thermal band bears complementary information to other spectral bands and despite the lower spatial resolution improves classification accuracy.

Abstract: This review paper offers a comprehensive exploration of the multifaceted applications of Unmanned Aerial Vehicles (UAVs) in various domains, showcasing their transformative impact in addressing complex challenges. The evaluation of cloud-based UAV systems' stability reveals their robustness and reliability, underlining their significance in numerous industries. Additionally, their role in enhancing robot navigation in intricate environments signifies a substantial advancement in robotics and automation. The integration of blockchain technology for secure Internet of Things (IoT) data transfer emphasizes the critical importance of data integrity and confidentiality in the IoT era. Furthermore, the optimization of energy-efficient data collection in IoT networks through UAVs demonstrates their potential to revolutionize data-driven decision-making processes, particularly in fields reliant on data accuracy and timeliness. The paper also highlights the application of deep reinforcement learning to enhance UAV-assisted IoT data collection, showcasing the synergy between advanced machine learning techniques and UAV technology. Finally, the discussion underscores the pivotal role of UAVs in precision agriculture, where they facilitate ecological farming practices and monitor environmental conditions, contributing to the pursuit of sustainable and efficient agriculture. This review reaffirms UAVs' status as transformative tools, reshaping industries and unlocking new frontiers of innovation and problem-solving. With ongoing technological advancements, UAVs are poised to play an increasingly central role in a wide range of applications, promising a future marked by ground breaking possibilities. Key findings include the dominance of the United States and China in the field, exploration of characteristics such as crop production, and innovative UAV-based methods for grassland mapping, maize growth assessment, and Arctic plant species monitoring. The research underscores the potential of UAVs in bridging field data and satellite mapping, providing valuable insights into diverse applications, from soil analysis to yield predictions, highlighting their transformative role in environmental monitoring and precision agriculture

On‐site soil analysis in the framework of precision agriculture is gaining significant importance to achieve improved crop productivity, increased soil health and reduced fertilizer application. In situ sensing techniques can provide the information required for decision support systems immediately on the field, for example, to control fertilization and liming. Shifted excitation Raman difference spectroscopy (SERDS) pilot investigations for on‐site soil analysis are presented using a portable SERDS sensor system specifically developed for in‐field studies. The SERDS sensor includes a dual‐wavelength diode laser at 785 nm integrated in an in‐house realized turnkey laser system and an optical power of 36 mW at the sample was chosen for our experiments. Outdoor pre‐investigations with the device and polystyrene as test sample show the capability of SERDS for qualitative and quantitative analysis under changing daylight conditions. On‐site soil analysis is carried out and SERDS extracts Raman signals from disturbing background interference with a 15‐fold improvement of the signal‐to‐background‐noise ratio. Beside others, closely neighboured Raman signals of calcite and dolomite are identified and even mixtures of both soil carbonates are discriminated using SERDS. The number of accumulations for generating an averaged SERDS spectrum of soil with a sufficient signal stability and signal‐to‐background‐noise ratio is evaluated to optimize the overall exposure time for such in situ experiments. The presented results demonstrate the large capability of the developed portable SERDS sensor system for on‐site soil investigations as promising tool for precision agriculture.

Air quality is a major concern in many large cities of the world. This paper studies the relationship between particulate matter of size less than 10-micron meter (PM10) and satellite observation from OCTS. The objective of this study is to map the PM10 distribution in Peninsular Malaysia using visible and thermal bands data. The in-situ PM10 measurements were collected simultaneously with the acquisition of the satellite image. The reflectance values in the visible and digital numbers in the thermal bands were extracted corresponding to the ground-truth locations and later used for algorithm regression analysis of the air quality. A developed algorithm was used to predict the PM10 values from the satellite image. The novelty of this study is the algorithm uses a combination of reflectance measurements from the visible bands and the corresponding apparent temperature values of the thermal band. This study investigates the relationship between the extracted OCTS signals and the PM10 values. The reflectance at 3.55-3.88 micro meter is computed after correction for the emission by the atmosphere. The surface emissivity values were computed based on the NDVI values. The developed algorithm produced a high correlation between the measured and estimated PM10 values of 0.97. Finally, a PM10 map was generated over Peninsular Malaysia using the proposed algorithm. This study has indicated the potential of OCTS satellite data for air quality study.

Thermal remote sensing is an important field in research of remote sensing. The authors performed a verification study on the brightness temperature derived from thermal infrared band image data of LANDSAT-7/enhanced thematic mapper plus (ETM+) and advanced spaceborne thermal emission and reflection radiometer (ASTER) for the detection of areas with abnormal high temperatures around Dali city in the southern part of China. As to the thermal infrared band, the functions for converting the digital number (DN) values of satellite imagery into the brightness temperature are introduced. Then, according to the brightness temperatures calculated, generate the density segmentation images and get the areas with high temperature. Finally, as the result of comparison of the density segmentation images derived from the satellite images and the temperature distribution map measured in the filed, the variance shows that the proposed method of high-temperature detection from satellite images is feasible in a way, but there are limitations.

Precision agriculture (PA) has emerged as a key strategy for optimizing agricultural production. Using data-driven technologies such as sensors and satellite imagery, PA improves the efficiency of agricultural processes. Accurate crop yield estimation is an essential component of PA. An important aspect of yield estimation within PA is the ability to assess and map spatial variations in yield in an agricultural field. Understanding these spatial patterns enables more precise management decisions and targeted interventions.Therefore, this study aimed to develop two regression approaches, multiple linear regression (MLR) and random forest regression (RFR), to estimate crop yield using sixteen input variables with a 6 m resolution. These variables were obtained using different sensors, reflecting the soil and crop spatial variability. The estimation performance of the studied approaches was assessed using the coefficient of determination (R²), showing very satisfactory results (R² > 0.85) for both approaches.The spatial distribution of barley yield was assessed, focusing on identifying areas of high and low productivity within the field. RFR demonstrated its ability to capture yield patterns. By incorporating spatial factors, RFR effectively modelled the varying yield potential in the crop field. Keywords—precision agriculture, multiple linear regression, random forest regression, spatial pattern, barley Acknowledgments: Financed by Ministerio de Ciencia e Innovación, Spain (PID2021-124041OB-C22)