Search

Carrot yield maps are an essential tool in supporting decision makers in improving their agricultural practices, but they are unconventional and not easy to obtain. The objective was to develop a method to generate a carrot yield map applying a random forest (RF) regression algorithm on a database composed of satellite spectral data and carrot ground-truth yield sampling. Georeferenced carrot yield sampling was carried out and satellite imagery was obtained during crop development. The entire dataset was split into training and test sets. The Gini index was used to find the five most important predictor variables of the model. Statistical parameters used to evaluate model performance were the root mean squared error (RMSE), coefficient of determination (R2) and mean absolute error (MAE). The five most important predictor variables were the near-infrared spectral band at 92 and 79 days after sowing (DAS), green spectral band at 50 DAS and blue spectral band at 92 and 81 DAS. The RF algorithm applied to the entire dataset presented R2, RMSE and MAE values of 0.82, 2.64 Mg ha&minus, 1 and 1.74 Mg ha&minus, 1, respectively. The method based on RF regression applied to a database composed of spectral bands proved to be accurate and suitable to predict carrot yield.

In Anbetracht des Kompromisses zwischen der Erzielung des höchsten Gewinns und der geringsten Umweltbelastung ist ein tiefes Verständnis der ökonomischen Folgen der Stickstoff (N) Düngung erforderlich. Die vorliegende Doktorarbeit liefert umfassende Einblicke in (i) die Auswirkungen des standortspezifischen N-Managements (SSNM) auf die Rentabilität und Risikominderung, (ii) die Auswirkungen von Unsicherheiten und Risikoeinflüssen auf optimale N-Düngergaben und (iii) das Potenzial und die Kosten der Vermeidung von Treibhausgas (THG) Emissionen durch N-Düngereduktion. Ein Modellierungsansatz wurde entwickelt, um die Wirkung von Ertrag und Proteingehalt, Wirtschafts- und Risikoauswirkungen sowie THG-Emissionen auf die N-Düngung zu simulieren. Die Ergebnisse der Arbeit zeigen, dass SSNM die Wirtschaftlichkeit verbessert, indem es eine höhere Weizenqualität und damit Preisprämien erzielt. SSNM reduziert das Risiko, die Backqualität nicht zu erreichen, und es gibt keine wesentlichen Nachteile beim Verlustrisikomanagement im Vergleich zum einheitlichen Management. Preisprämien für eine höhere Weizenqualität bieten Anreize für höhere N-Düngergaben. Prämien verflachen die Gewinnfunktion weiter, was unzureichende Argumente für eine Absenkung des N-Inputs aus der Wirtschaftlichkeitssicht liefert, selbst bei einer hohen Risikoaversion der Landwirte. Eine moderate Reduzierung der mineralischen N-Düngung kann die THG-Emissionen bei moderaten Opportunitätskosten mindern. Die THG-Vermeidung durch N-Düngereduktion in einer bestimmten Region kann unter Berücksichtigung kultur- und ertragszonenspezifischer Ertragswirkungen optimiert werden. Insgesamt liefert diese Arbeit wichtige Erkenntnisse über die Chancen und Nachteile der Anpassung der N-Düngergaben. Darüber hinaus leistet sie einen direkten Beitrag zur Identifizierung von kosten- und risikoeffizienten N-Managementoptionen und bildet die Grundlage für effektive politische Ansätze zur THG-Vermeidung durch selektive N-Düngereduktion. Considering the tradeoff between achieving the highest profit and causing the lowest environmental impact, there is a need for a profound understanding of the economic consequences of nitrogen (N) fertilizer application. The present doctoral research provides comprehensive insights into (i) effects of site-specific N management (SSNM) on profitability and risk mitigation; (ii) impacts of uncertainties and risk implications on optimal N fertilizer rates; and (iii) potential and costs of mitigating greenhouse gas (GHG) emissions by N fertilizer reduction. A modelling approach was developed to simulate the response of yield, protein, economic and risk implications, and GHG emissions to N fertilizer application. Findings of the thesis show that SSNM improves profitability by achieving higher grain quality, thus, price premiums. SSNM reduces the risk of not reaching the baking grain quality and poses no considerable disadvantage on downside risk management compared to uniform management. Price premiums for higher wheat quality provide incentives for higher N input rates. Premiums further flatten the profit function, giving insufficient arguments for lowering N input from a farm profitability perspective, even in presence of high risk aversion of farmers. Moderate reduction of mineral N fertilizer can mitigate GHG emissions at moderate opportunity costs. GHG mitigation by N fertilizer reduction in a given region can be optimized considering crop and yield-zone-specific yield responses. Overall, this thesis provides important insights on chances and drawbacks of adjusting N fertilizer rates. Moreover, it makes a direct contribution in identifying cost- and risk-efficient N management options and provides a basis for effective policy approaches to reduce GHG emissions by selective N fertilizer reduction.

International audience; Yield is one of the key indicators in agriculture. The most common practices provide only one yield value for a whole field according to the weight of the harvested crop. On the contrary, precision agriculture techniques discover spatial patterns within a field to minimise the environmental burden caused by agricultural activities. Field harvesters equipped with sensors provide more detailed and spatially localised values. The measurements from such sensors need to be filtered and interpolated for the purposes of follow-up analyses and interpretations. This study verified the differences between three methods of interpolation (Inverse Distance Weighted, Inverse Distance Squared and Ordinary Kriging) derived from field sensor measurements that were (1) obtained directly from the field harvester, (2) processed by global filters, and (3) processed by global and local filters. Statistical analyses evaluated the results of interpolations from three fully operational Czech fields. The revealed spatial patterns, as well as recommendations regarding the suitability of the interpolation methods used, are presented at the end of this paper.

The present dataset contains colour images acquired in a commercial Fuji apple orchard (Malus domestica Borkh. cv. Fuji) to reconstruct the 3D model of 11 trees by using structure-from-motion (SfM) photogrammetry. The data provided in this article is related to the research article entitled “Fruit detection and 3D location using instance segmentation neural networks and structure-from-motion photogrammetry” [1]. The Fuji-SfM dataset includes: (1) a set of 288 colour images and the corresponding annotations (apples segmentation masks) for training instance segmentation neural networks such as Mask-RCNN; (2) a set of 582 images defining a motion sequence of the scene which was used to generate the 3D model of 11 Fuji apple trees containing 1455 apples by using SfM; (3) the 3D point cloud of the scanned scene with the corresponding apple positions ground truth in global coordinates. With that, this is the first dataset for fruit detection containing images acquired in a motion sequence to build the 3D model of the scanned trees with SfM and including the corresponding 2D and 3D apple location annotations. This data allows the development, training, and test of fruit detection algorithms either based on RGB images, on coloured point clouds or on the combination of both types of data. This work was partly funded by the Secretaria d'Universitats i Recerca del Departament d'Empresa i Coneixement de la Generalitat de Catalunya (grant 2017 SGR 646), the Spanish Ministry of Economy and Competitiveness (project AGL2013-48297-C2-2-R) and the Spanish Ministry of Science, Innovation and Universities (project RTI2018-094222-B-I00). Part of the work was also developed within the framework of the project TEC2016-75976-R, financed by the Spanish Ministry of Economy, Industry and Competitiveness and the European Regional Development Fund (ERDF). The Spanish Ministry of Education is thanked for Mr. J. Gené’s pre-doctoral fellowships (FPU15/03355). We would also like to thank Nufri (especially Santiago Salamero and Oriol Morreres) and Vicens Maquinària Agrícola S.A. for their support during data acquisition, and Ernesto Membrillo and Roberto Maturino for their support in dataset labelling.

In the United States average adoption rates have increased for precision agriculture (PA) technologies used to produce many field crops. PA makes use of information collected on the farm to target site-specific, intensive management of farm production. The United States Department of Agriculture (USDA) Agricultural Resource Management Survey (ARMS) allows close examination of regional patterns of adoption, and how crop types and region interact with differences in farm sizes and soil productivity variability to influence adoption rates. The most common PA technologies are guidance systems that use global positioning systems (GPS) to steer tractors and other farm equipment. Remote sensing, soil mapping, and yield mapping all use GPS to geolocate data and create maps used to guide farm management decision. Variable rate input-application technologies (VRT) make use of remote images, soil tests, yields maps and other sources of information to apply different, more precise levels of inputs in farmer’s fields. GPS guided VRT fertilization was introduced in the early 1990s and increased slowly over the last three decades. The ARMS data for winter wheat (2017), corn (2016) and soybeans (2012) showed use of VRT seeding and pesticide applications growing rapidly. The data indicated that PA technology was being used on farms across all sizes and all regions, with adoption occurring more rapidly on larger farms. VRT use on soybean farms was highest in areas of higher soil variability.

The concept of precision agriculture (PA) is becoming an interesting idea for managing natural resources and realizing modern sustainable agricultural development. The general objective of this study is to better understanding of the current use of PA practices in Florida, USA. Specific objectives were to identify PA trends, information source preferences and the constraints to wider use of PA technology. Online and in-person survey results were collected and analyzed to provide an overview of the adoption for specific PA technologies in Florida and compared grower-reported challenges of adoption and attitudes to those found in 2005. In 2018, the plant tissue sampling was the highest PA technic that grower used (81.6%) while in 2005, the highest rate was for using GPS receivers and Soil variability mapping (16.1%). In the meantime, growers had plan to use remote sensing as well as sensor based variable rate applicator (77.3 and 77.7%) in 2005 whilst the more demanding technic for grower in 2018 was yield mapping (27.27%). And the main reason for not adapting PA technology was vary based on the technics individually for both years. However, the most common response for not using PA in general referred to the producer satisfaction with their current production practices, for all of the investigated technologies in 2005 and 2018. The second most common reason for not adapting PA technology was lack of information in 2005 while it was lack of capital in 2018. Respondents were also questioned on their “adoption attitude”. In 2018, 37.29 % described themselves as the first one who like to try new technology and method while in 2005, 16.1% showed their interest to work with new method and technology. In both years, the best description of starting new technology was “normally wait to see other's success with new technologies and production methods” which were categorized at “coat-tailors”.

The agricultural industry is increasingly reliant upon the development of technologies that employ real-time monitoring of machine performance to generate pertinent information for machine operators, owners, and managers. Yield mapping in particular is an important component of implementing precision agricultural practices and assessing spatial variability. In an attempt to generate yield maps in sugarcane, this research estimated yield in the field based on GPS data from harvesters, tractors and semi-trucks. The method was based on identifying “fill events”, which represent a distance through which the tractor/wagon combination traveled in parallel with the harvester, indicating that the wagon was being filled. Each wagon was filled to approximately 10 Mg of sugarcane, which was divided by the fill event distance and row width to determine the yield in Mg ha−1. A total of 76 fill events were observed from a 7.1 ha harvested area. Based on the estimated yield per fill event, a rudimentary yield map was developed, which was expanded into a generalized yield map for the 7.1 ha harvested area.

Strawberries in California have a $2 billion direct economic impact on the state; however, they are currently produced based only on uniform field management techniques. Creating yield maps of strawberries could allow for variable-rate and site-specific applications of inputs, which could improve productivity and reduce environmental pollution. This paper presents the development and application of an instrumented strawberry-picking cart for yield mapping. During manual harvest of strawberries planted on raised beds, pickers walk inside the furrows, pick fruit from the beds on both sides, and deposit them into a tray placed on a picking cart. A ‘smart’ picking cart, similar to the standard carts, has been designed and instrumented with several types of sensors including load cells, a real-time kinematic global positioning system (RTK GPS), a microcontroller, and an inertial measurement unit (IMU). This instrumented cart serves two purposes: to work in sync with tray-transporting robots during robot-aided strawberry harvesting, and to create yield maps of strawberry fields. A yield map for an approximately 300 m 2 plot of a strawberry field in Salinas, California, was generated after the cart was calibrated. During the yield-monitoring experiment, 13.5 trays, each with a capacity of about 4.2 k g of strawberries, were filled with fruit. The mean prediction accuracy of the mass of full trays measured by the load cells was calculated to be 4.8 % .

A machine vision algorithm was developed to detect passion fruits and identify maturity of the detected fruits using natural outdoor RGB-D images. As different passion fruits on the same branch can be in different maturity stages, detection and maturity classification on a complex background are very important for yield mapping and development of intelligent mobile fruit-picking robots. In this study, a Kinect sensor was used for data acquisition, and maturity stages of the fruits were divided into five categories: young (Y), near-young (NY), near-mature (NM), mature (M) and after-mature (AM). The algorithm involved two stages. First, by colour and depth images, passion fruits were detected using faster region-based convolutional neural networks (Faster R-CNN), and colour-based detection was integrated with depth-based detection for improving detection performance. Second, for each detected fruit region, the dense scale invariant features transform (DSIFT) algorithm combined with locality-constrained linear coding (LLC) was used to extract and represent the features of fruit maturity from R, G, and B channels, respectively. In addition, the RGB-DSIFT-LLC features were input into a linear support vector machine (SVM) classifier for identifying the maturity of fruits. By conducting an experimental study on a special dataset, we verified that the proposed method achieves 92.71% detection accuracy and 91.52% maturity classification accuracy.

Citrus fruit detection is one of the most important and challenging steps in citrus yield mapping. The distinct color differences between the ripe fruit and leaves allowed previously-described imaging-based methods to achieve good results. However, immature green citrus fruit detection, which aims to provide valuable information for citrus yield mapping at earlier stages is much more difficult because the fruit and leaf colors are very similar. This study combines color and thermal images for immature green fruit detections. Experiments identified optimal conditions for thermal imaging. A multimodal imaging platform was built to integrate color and thermal cameras. A novel image registration method was developed for combining color and thermal images and matching fruit in both images which achieved pixel-level accuracy. A new Color-Thermal Combined Probability (CTCP) algorithm was created to effectively fuse information from the color and thermal images to classify potential image regions into fruit and non-fruit classes. Algorithms were also developed to integrate image registration, information fusion and fruit classification and detection into a single step for real-time processing. An increase in recall rate from 78.1% when using only color images to 90.4% after fusing the color and thermal images was obtained at similar precision rates, and an increase in precision rate from 86.6% to 95.5% was obtained at similar recall rates. The fusion of the color and thermal images effectively improved immature green citrus fruit detection.

Damage to agricultural crops due to water-logging is becoming more frequent in this era of global climate change. In this study, we investigated the effect of water-logging on winter wheat growth (LAI and aboveground biomass) and yield at a parcel scale using high spatial resolution satellite data. For this purpose, a dynamic mapping of winter wheat LAI and biomass during growth under water-logging conditions was implemented. In addition, yield mapping and yield loss estimation were also carried out to arrive at the potential impacts of water-logging on both winter wheat growth and grain yield. Two varieties of winter wheat were investigated (Yang Mai 14 and Yang Mai 18) at tillering, jointing to booting and flowering. Field conditions were representative of water-logging treatment (contrast check (CK), waterlogging (WL) and flooding (FL)). A total of eight high spatial resolution optical satellite images, including WorldView-2, WorldView-3, Pleiades-1A, SPOT-6, GeoEye-1 and SPOT-7 were obtained at time points concurrent with eight temporal field observations. Seven widely used vegetation indices (VIs) were utilized as independent variables for LAI, biomass and yield estimation. Optimal estimation models were selected according to coefficient of determination (R2), correlation coefficient (R) and root mean square error (RMSE) for subsequent mapping of LAI, biomass and yield. Results show that the power model, having EVI as the independent variable, had the highest accuracy for biomass estimation (R2 of 0.78 and RMSE of 0.076 kg/m2) while the exponential model with NDVI is the optimal model for LAI estimation (with 0.74 in R2 and 0.64 in RMSE). GNDVI is the optimal VI for yield mapping, with 0.563 in Rcv (cross validated R) and 843.76 kg/hm2 in RMSEcv (cross validated RMSE). As for the assessment of water-logging damage on winter wheat growth, FL showed a more serious impact than that of WL, based on results of the dynamic mapping of biomass and LAI at the same development stages. Water-logging from jointing to booting showed a more serious damage impact with respect to biomass and yield than that at the tillering and flowering stages. Our results have demonstrated the potential of multi-source and high spatial resolution remotely-sensed optical data for quantifying the impact of water-logging on winter wheat growth and grain yield at parcel scales, a research direction that has rarely been reported in agricultural remote sensing literature. This study thus provides a fundamental basis and the possibility for crop yield loss evaluation, water-logging monitoring, and for the design of mitigation strategies that would benefit even small-holder and subsistence farmers.

A survey of Australian grain growers was conducted to gauge grower attitudes to crop and soil sensing and their role in nitrogen fertilizer management. The technologies considered were yield monitors, remote and proximal crop sensing, high resolution soil survey, soil moisture sensing and digital elevation models (DEM). Whereas Australian grain growers have readily adopted machine guidance and autosteer, and a majority have access to yield monitoring, the rate of use of many crop and soil sensors remains comparatively low. However, the survey results suggest a positive effect on sensor adoption through present use of yield mapping. Access to yield maps was significantly associated with the use of remotely sensed imagery, high resolution soil survey, soil moisture sensing, DEM and variable rate application of fertilizers and/or soil amendments. There is some support for proximal crop sensing, albeit with low present rates of use; the use of soil water sensors and DEM is presently very low. For the further development of precision agriculture (PA), the results make clear that expending effort in enhancing the adoption and use of yield maps would be valuable as a lever to gain ‘buy-in’ from growers to sensing and PA more broadly. Since growers use many sources of information to support fertilizer decision-making, any new fertilizer decision aid needs to establish a point of difference from, but be complementary to, existing tools. One way of achieving this would be to use sensors, supported by locally derived algorithms, as a key input to fertilizer decision support.

Hemp (Cannabis sativa L.) is a multipurpose industrial crop which is mainly cultivated in temperate regions. With its high potential for economic returns for its seeds and fiber, there is growing interest in cultivating hemp in many territories including Malaysia and other Asian countries, where its cultivation is currently illegal. To date, no comprehensive study on the suitability of this crop under Malaysian conditions has been conducted. In this paper, we propose an assessment framework as a roadmap to develop the hemp industry in Malaysia and possibly other Asian countries with equatorial climates. This framework includes suitability assessment (climate and soil), crop modelling (current and future yields under climate change) and economic analysis (net present value (NPV), NPV benefit (NPVB) and benefit-cost ratio (BCR). The land suitability assessment classified hemp as an adaptable crop for most of the land in the country. The AquaCrop model, parameterised from secondary data collected from literature was used in simulations and potential yield mapping. The estimated average potential seed and fiber yield at six locations between 2010 and 2019 was 1.61 ± 0.25 and 2.78 ± 0.39 t ha–1 respectively. Using five general circulation model (GCM) simulations, yields under future climates in Malaysia showed an increase in most of the locations. The highest NPVB of 1641 USD ha–1 (BCR of 1.33) for seed was estimated under current climate conditions. Yields of 1.38 t ha–1 (seed) and 3.62 t ha–1 (fiber) are the minimum economically feasible yields with a Benefit-Cost Ratio of 1.00 suggesting a potential for hemp cultivation in comparison to countries with established hemp industries. The present framework could be used to develop a pathway for adoption of hemp as a crop for the future in tropical countries.

Apart from socioeconomic factors, success of robotics in agriculture lies in developing economically attractive solutions with efficiency comparable to that of the humans. Fruit localization is one of the building blocks in many robotic agricultural operations (e.g., yield mapping and robotic harvesting) that determines 3D Euclidean positions of the fruits using one or several sensors. It is crucial to guarantee the performance of the localization methods in the presence of fruit detection errors and unknown fruit motion (e.g., due to wind gust), so that the desired efficiency of the subsequent systems can be achieved. For instance, inaccurate localization may severely affect fruit picking efficiency in robotic harvesting. The presented estimation-based localization approach provides estimates of the fruit positions in the presence of fruit detection errors and unknown fruit motion, and it is based on a new sensing procedure that uses multiple (⩾2) inexpensive monocular cameras. A nonlinear estimator called particle filter is developed to estimate the unknown position of the fruits using image measurements obtained from multiple cameras. The particle filter is partitioned into clusters to independently localize individual fruits, while the behavior of the clusters is manipulated at global level to maintain a single filter structure. Since the accuracy of localization is affected by errors in fruit detection, the presented sensor model includes non-Gaussian fruit detection errors along with image noise. Fruit motion can significantly reduce harvesting efficiency due to errors in locating moving fruits. In contrast to existing methods, the dynamics of fruit motion are derived and included in the localization framework to obtain time-varying position estimates of the moving fruits. A detailed theoretical foundation is provided for the new estimation-based fruit localization approach, and it is validated through extensive Monte Carlo simulations. The performance of the estimator is evaluated by varying the design parameters, measurement noise, number of fruits, amount of overlap in clustered fruit scenarios, and fruit velocity. Correlation of these parameters with the performance of the estimator is derived, and guidelines are presented for selecting the design parameters and predicting performance bounds under given operating conditions.

Yield mapping techniques have only recently started to be implemented by the Californian wine grape industry, but the advancement has necessitated new processing methods for large vineyards. The process for mapping large blocks harvested with multiple machines has only recently occurred and implies that their yield monitors have to be calibrated and corrected to the same scale. Here we discuss two methods for processing yield maps at the commercial level. Method 1 depends on many calibrations with delivered fruit weight to a winery. Method 2 normalizes raw files automatically can reduce total processing time by up to 90%.

The mapping of sugarcane yield is still not as widely available as it is for grain crops. Sugarcane harvesters cut and process the cane in a single or maximum of two rows, facilitating the monitoring of cane yield and its behavior on a small scale. This study tested a method for sugarcane yield data cleaning, investigating if the data recording frequency influences the characterization of yield variations in mapping high-resolution spatial data within a single row. Four data sets from yield monitors of single row harvesting were used. A cleaning process with global and anisotropic filtering in a single sugarcane row was applied. The local outlier cleaner compares the yield value of a point with its nearest neighbors within the same row. Even after the elimination of outliers, there is great variation in yield between the rows, and this variation is much smaller in a single row. A frequency of 2 Hz was required for identifying and characterizing small yield variations within the sugarcane rows whilst other frequencies tried (0.2 and 0.1 Hz) resulted in loss of information on yield variability within the row. The difference between the root mean square error (RMSE) of ordinary kriging (OK) and inverse distance weighting (IDW) techniques is large enough to suggest the use of an individual yield line. Individual yield lines saved information in the data generated by the yield monitor unlike IDW and OK interpolation methods which omitted information over short distances within the rows and compromised the quality of high-resolution maps.

Yield mapping is a subject of research in (precision) agriculture and one of the primary concerns for farmers as it forms the basis of their income and has implications for subsidies and taxes. The presented approach involves deployment of field harvesters equipped with sensors that provide more detailed and spatially localized values than merely a sum of yields for the whole plot. The measurements from such sensors need to be filtered and subject to further processing, including interpolation, to facilitate follow-up interpretation. This paper aims to identify the relative differences between interpolations from (1) (field) measured data, (2) measured data that were globally filtered, and (3) measured data that were globally and locally filtered. All the measured data were obtained at a fully operational farm and are considered to represent a natural experiment. The revealed spatial patterns and recommendations regarding global and local filtering methods are presented at the end of the paper. Time investments into filtering techniques are also taken into account.

Accurate crop yield estimates are important for governments, farmers, scientists and agribusiness. This paper provides a novel demonstration of the use of freely available Sentinel-2 data to estimate within-field wheat yield variability in a single year. The impact of data resolution and availability on yield estimation is explored using different combinations of input data. This was achieved by combining Sentinel-2 with environmental data (e.g. meteorological, topographical, soil moisture) for different periods throughout the growing season. Yield was estimated using Random Forest (RF) regression models. They were trained and validated using a dataset containing over 8000 points collected by combine harvester yield monitors from 39 wheat fields in the UK. The results demonstrate that it is possible to produce accurate maps of within-field yield variation at 10 m resolution using Sentinel-2 data (RMSE 0.66 t/ha). When combined with environmental data further improvements in accuracy can be obtained (RMSE 0.61 t/ha). We demonstrate that with knowledge of crop-type distribution it is possible to use these models, trained with data from a few fields, to estimate within-field yield variability on a landscape scale. Applying this method gives us a range of crop yield across the landscape of 4.09 to 12.22 t/ha, with a total crop production of approx. 289,000 t.

Yield prediction is of great significance for yield mapping, crop market planning, crop insurance, and harvest management. Remote sensing is becoming increasingly important in crop yield prediction. Based on remote sensing data, great progress has been made in this field by using machine learning, especially the Deep Learning (DL) method, including Convolutional Neural Network (CNN) or Long Short-Term Memory (LSTM). Recent experiments in this area suggested that CNN can explore more spatial features and LSTM has the ability to reveal phenological characteristics, which both play an important role in crop yield prediction. However, very few experiments combining these two models for crop yield prediction have been reported. In this paper, we propose a deep CNN-LSTM model for both end-of-season and in-season soybean yield prediction in CONUS at the county-level. The model was trained by crop growth variables and environment variables, which include weather data, MODIS Land Surface Temperature (LST) data, and MODIS Surface Reflectance (SR) data, historical soybean yield data were employed as labels. Based on the Google Earth Engine (GEE), all these training data were combined and transformed into histogram-based tensors for deep learning. The results of the experiment indicate that the prediction performance of the proposed CNN-LSTM model can outperform the pure CNN or LSTM model in both end-of-season and in-season. The proposed method shows great potential in improving the accuracy of yield prediction for other crops like corn, wheat, and potatoes at fine scales in the future.

Made available in DSpace on 2019-10-06T05:28:55Z (GMT). No. of bitstreams: 0 Previous issue date: 2019-08-01 Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES) Among the main techniques employed in precision agriculture, yield mapping and automatic guidance of agricultural machines are the best-known to farmers. The objective of this study was to evaluate, using statistical process control tools, the quality of automatic guidance using satellite signals, to reduce positioning errors and losses in peanut digging. The treatments consisted of the use of manual (operator guidance) and automatic (autopilot) guidance with RTX satellite signals in sowing and digging operations. The quality of the operation was evaluated after collection of 30 points spaced at 100m for each quality indicator, which are the losses and the errors of alignment of the mechanised sets in sowing and digging operations. From the perspective of statistical control, manual guidance was shown to be compromised for the quality indicators of digging losses. Despite the instability in the sowing and digging operations, the use of automatic guidance proved to be accurate. The use of automatic guidance increases the precision and reduces overlaps (

Agricultural activities conducted in the Great Rift Valley of Kenya show a significant decline of productivity levels. This phenomenon is mainly related to limited availability of water resources, lack of supporting irrigation, and harvesting techniques ineffectiveness. Production risks reduction is closely related with a better use of water resources and a better understanding of the effects resulting from the multiple interactions between climate, agricultural vegetation, soil type, and crops management techniques. In this paper, a remote and automatic agricultural monitoring system is presented as an effective alternative to the most traditional in situ measurements and observations.We investigated the use of phenological information extracted from satellite imagery combined with crop calendar and supported by agro-ecological zoning (AEZ) in accurate crop classification and monitoring. Vegetation indices extracted from Landsat 8 imagery are capable to track the vegetation development through the year, then phenological profiles can be extracted and implemented into a multitemporal automatic classification process to detect agricultural areas and to discriminate among different crop species. The phenological profiles extracted by satellite imagery are compared with crop calendar data compiled by FAO for the area of interest. The classification procedure is supported by AEZs based on crop modeling and environmental matching procedures in order to identify crop-specific environmental limitations under assumed levels of inputs and management conditions. The FAO crop water productivity model AquaCrop is calibrated for wheat and maize yield mapping in the central highland of Kenya, handling both environmental and phenological data. The combined use of phenological data and AEZs results in a robust methodology with a classification overall accuracy of 91.35%. A good model performance is obtained relative to yield predictions, with R of 0.69 and 0.72.

The objective of this work was to investigate the use of remotely sensed vegetation indices to improve the quality of yield maps. The method was applied to the yield data of twelve cornfields from the Data Intensive Farm Management project. The results revealed the need to time shift the yield values up to three seconds to better match the sensor readings with the geographic coordinates. The residuals of the yield prediction model were used to identify points with unlikely yield values for that location, as an alternative to traditional approaches using local spatial statistics, without any assumption of spatial dependence or stationarity. The temporal and spatial distribution of the standardized coefficients for each experimental unit highlighted the presence of trends in the data. At least five out of the twelve fields presented trends that could have been induced by data collection.

The availability of big data in agriculture, enhanced by free remote sensing data and on-board sensor-based data, provides an opportunity to understand within-field and year-to-year variability and promote precision farming practices for site-specific management. This paper explores the performance in durum wheat yield estimation using different technologies and data processing methods. A state-of-the-art data cleaning technique has been applied to data from a yield monitoring system, giving a good agreement between yield monitoring data and hand sampled data. The potential use of Sentinel-2 and Landsat-8 images in precision agriculture for within-field production variability is then assessed, and the optimal time for remote sensing to relate to durum wheat yield is also explored. Comparison of the Normalized Difference Vegetation Index(NDVI) with yield monitoring data reveals significant and highly positive linear relationships (r ranging from 0.54 to 0.74) explaining most within-field variability for all the images acquired between March and April. Remote sensing data analyzed with these methods could be used to assess durum wheat yield and above all to depict spatial variability in order to adopt site-specific management and improve productivity, save time and provide a potential alternative to traditional farming practices.