Browsing by Subject "Precision farming"

Now showing 1 - 11 of 11

A study of integrated weed control strategies for establishing soybean (Glycine max L. MERR.) in the German production system
(2017) Weber, Jonas Felix; Gerhards, Roland
Soybean (Glycine max L. MERR.) has expanded to become one of the most traded agriculture products worldwide in recent decades. Europe is one of the primary importing regions; however, the dependence on soybean imports has been critically assessed by the public. To reduce the dependency on soybean imports, increased local soybean production should be favoured. In addition to environmental conditions, weeds are a major limiting factor for soybean yield under German climate conditions. Weeds can be successfully controlled with herbicides, although crop injury frequently occurs after application. Sensor-based screening would be helpful for a rapid evaluation of cultivar tolerance to herbicide application. Alternatively, mechanical weed control strategies can be applied. Since soybean production is currently introduced to the regional crop production, weed control efficiency of conventional mechanical tools (e.g., hoeing and harrowing) have to be evaluated. By using automatic guiding systems intra-row elements could be utilised to increase the weed control efficiency of mechanical hoeing. Other than that, agronomical practices such as the tillage system or cover crops influences the occurrence of weeds. The most common practise worldwide for soybean cultivation is the no-tillage system, which has not yet been investigated under local conditions. Therefore, different weed control strategies in soybean production were investigated according to the following major objectives of this thesis: - Detection of crop injury by herbicides using a chlorophyll fluorescence imaging sensor for different soybean cultivars. - Evaluation of the conventional mechanical strategies of hoeing and harrowing in soybean. - Examination of the weed control efficiency in inter- and intra-row areas using RTK-GNSS precision steering and an optical camera guiding system for mechanical weed control in soybean. - Evaluation of the efficiency of ‘tillage’, ‘reduced tillage’ and ‘no- tillage’ cultivation systems and the influence of cover crops on weed suppression in local soybean production. The Imaging-PAM-sensor based on chlorophyll fluorescence imaging was utilised to investigate the response of different soybean cultivars to the application of herbicides. The measurements indicated significant differences with respect to injury to the cultivars after herbicide application. Herbicides containing the active ingredient ‘metribuzin’ resulted in significant differences in the level of crop injury depending on the cultivar. The active ingredients ‘dimethenamid’ and ‘clomazone’ resulted in less injury, independent of the cultivar. The PAM-sensor was able to detect stress symptoms 3 to 7 days before visual symptoms appeared. An investigation of hoeing and harrowing, which are conventional mechanical techniques for weed control, showed 78% and 72% weed control efficiency, respectively. In further experiments, the results of precision steering systems using RTK-GNSS and an optical camera guiding system additionally equipped with intra-row elements (e.g., finger weeders) were compared with the results of conventional hoeing. Mechanical weed control using automatic steering technology and an intra-row element (finger weeder) reduced the weed density by 89% compared with 68% in the conventional hoeing system. With respect to crop yields, statistical benefits of precision steering were not observed. However, the driving speed could be increased from 4 km h−1 in the conventional hoeing system to 10 km h−1 using the automatic steering systems. In an additional experiment, two cover crops species, rye (Secale cereale L.) and barley (Hordeum vulgare L.), were grown for preventive weed control in soybean production. The cover crops were transformed into a mulch layer using a roller-crimper immediately before soybean was sown using a no-tillage technique. Conventional tillage was performed to compare the systems with respect to their weed control efficiency, crop development and soybean yield. The results showed that the no-tillage system had a greater effect on suppressing summer annual weed species (Chenopodium album (L.), Echinochloa crus-galli (L.) P. Beauv. and Amaranthus retroflexus (L.)) than the tillage systems. Conventional tillage and reduced tillage showed increased suppression of the weed species Matricaria inodora (L.), Stellaria media (L.) Vill. and Sonchus arvensis (L.), which were present in the no-tillage system. However, in the conventional tillage and reduced tillage systems, an additional weed control treatment was necessary to suppress the summer annual weeds and ensure high yields. The cover crop rye resulted in weed control similar to that of barley in the no-tillage system. Despite the low weed density, the no-tillage system with a rolled cover crop showed a yield reduced of 47%, whereas the yield of the reduced tillage system was decrease by 23% compared with the conventional tillage system.
Advances in site-specific weed management in agriculture: A review
(2022) Gerhards, Roland; Andújar Sanchez, Dionisio; Hamouz, Pavel; Peteinatos, Gerassimos G.; Christensen, Svend; Fernandez‐Quintanilla, Cesar
The developments of information and automation technologies have opened a new era for weed management to fit physical and chemical control treatments to the spatial and temporal heterogeneity of weed distributions in agricultural fields. This review describes the technologies of site‐specific weed management (SSWM) systems, evaluates their ecological and economic benefits and gives a perspective for the implementation in practical farming. Sensor technologies including 3D cameras, multispectral imaging and Artificial Intelligence (AI) for weed classification and computer‐based decision algorithms are described in combination with precise spraying and hoeing operations. Those treatments are targeted for patches of weeds or individual weed plants. Cameras can also guide inter‐row hoes precisely in the centre between two crop rows at much higher driving speed. Camera‐guided hoeing increased selectivity and weed control efficacy compared with manual steered hoeing. Robots combine those guiding systems with in‐row hoeing or spot spraying systems that can selectively control individual weeds within crop rows. Results with patch spraying show at least 50% saving of herbicides in various crops without causing additional costs for weed control in the following years. A challenge with these technologies is the interoperability of sensing and controllers. Most of the current SSWM technologies use their own IT protocols that do not allow connecting different sensors and implements. Plug & play standards for linking detection, decision making and weeding would improve the adoption of new SSWM technologies and reduce operational costs. An important impact of SSWM is the potential contribution to the EU‐Green Deal targets to reduce pesticide use and increase biodiversity. However, further on‐farm research is needed for integrating those technologies into agricultural practice.
A comparison of seven innovative robotic weeding systems and reference herbicide strategies in sugar beet (Beta vulgaris subsp. vulgaris L.) and rapeseed (Brassica napus L.)
(2023) Gerhards, Roland; Risser, Peter; Spaeth, Michael; Saile, Marcus; Peteinatos, Gerassimos
More than 40 weeding robots have become commercially available, with most restricted to use in crops or fallow applications. The machines differ in their sensor systems for navigation and weed/crop detection, weeding tools and degree of automation. We tested seven robotic weeding systems in sugar beet and winter oil‐seed rape in 2021 and 2022 at two locations in Southwestern Germany. Weed and crop density and working rate were measured. Robots were evaluated based on weed control efficacy (WCE), crop stand loss (CL), herbicide savings and treatment costs. All robots reduced weed density at least equal to the standard herbicide treatment. Band‐spraying and inter‐row hoeing with RTK‐GPS guidance achieved 75%–83% herbicide savings. When hoeing and band spraying were applied simultaneously in one pass, WCE was much lower (66%) compared to the same treatments in two separate passes with 95% WCE. Hoeing robots Farmdroid‐FD20®, Farming Revolution‐W4® and KULTi‐Select® (+finger weeder) controlled 92%–94% of the weeds. The integration of Amazone spot spraying® into the FD20 inter‐row and intra‐row hoeing system did not further increase WCE. All treatments caused less than 5% CL except for the W4‐robot with 40% CL and the combination of conventional inter‐row hoeing and harrowing (21% CL). KULT‐Vision Control® inter‐row hoeing with the automatic hydraulic side‐shift control resulted in 80% WCE with only 2% CL. Due to the low driving speed of maximum 1 km h−1 of hoeing robots with in‐row elements, treatment costs were high at 555–804 € ha−1 compared to camera‐guided inter‐row hoeing at 221 € ha−1 and broadcast herbicide application at 307–383 € ha−1. Even though the costs of robotic weed management are still high, this study shows that robotic weeding has become a robust, and effective weed control method with great potential to save herbicides in arable and vegetable crops.
Crop plant reconstruction and feature extraction based on 3-D vision
(2019) Vázquez Arellano, Manuel; Griepentrog, Hans
3-D imaging is increasingly affordable and offers new possibilities for a more efficient agricul-tural practice with the use of highly advances technological devices. Some reasons contrib-uting to this possibility include the continuous increase in computer processing power, the de-crease in cost and size of electronics, the increase in solid state illumination efficiency and the need for greater knowledge and care of the individual crops. The implementation of 3-D im-aging systems in agriculture is impeded by the economic justification of using expensive de-vices for producing relative low-cost seasonal products. However, this may no longer be true since low-cost 3-D sensors, such as the one used in this work, with advance technical capabili-ties are already available. The aim of this cumulative dissertation was to develop new methodologies to reconstruct the 3-D shape of agricultural environment in order to recognized and quantitatively describe struc-tures, in this case: maize plants, for agricultural applications such as plant breeding and preci-sion farming. To fulfil this aim a comprehensive review of the 3-D imaging systems in agricul-tural applications was done to select a sensor that was affordable and has not been fully inves-tigated in agricultural environments. A low-cost TOF sensor was selected to obtain 3-D data of maize plants and a new adaptive methodology was proposed for point cloud rigid registra-tion and stitching. The resulting maize 3-D point clouds were highly dense and generated in a cost-effective manner. The validation of the methodology showed that the plants were recon-structed with high accuracies and the qualitative analysis showed the visual variability of the plants depending on the 3-D perspective view. The generated point cloud was used to obtain information about the plant parameters (stem position and plant height) in order to quantita-tively describe the plant. The resulting plant stem positions were estimated with an average mean error and standard deviation of 27 mm and 14 mm, respectively. Additionally, meaning-ful information about the plant height profile was also provided, with an average overall mean error of 8.7 mm. Since the maize plants considered in this research were highly heterogeneous in height, some of them had folded leaves and were planted with standard deviations that emulate the real performance of a seeder; it can be said that the experimental maize setup was a difficult scenario. Therefore, a better performance, for both, plant stem position and height estimation could be expected for a maize field in better conditions. Finally, having a 3-D re-construction of the maize plants using a cost-effective sensor, mounted on a small electric-motor-driven robotic platform, means that the cost (either economic, energetic or time) of gen-erating every point in the point cloud is greatly reduced compared with previous researches.
Development of a sensor-based harrowing system using digital image analysis to achieve a uniform weed control selectivity in cereals
(2021) Spaeth, Michael; Gerhards, Roland
Using intelligent sensor technology for site-specific weed control can increase the efficacy of traditional weed control implements. Several scientific studies successfully used intelligent sensors for automatic harrow control by taking many different parameters into account such as weed density, soil resistance factor, and plant growth. However, none of the systems was practically feasible because these factors made the control system too complex and unattractive for farmers. Defining only one parameter (crop soil cover) instead of many provides a new and simple approach which was investigated in this work. The first scientific publication focuses on the development, practical implementation and testing of the automatic harrow control system. Two RGB-cameras were mounted before and after the harrow and constantly monitored crop cover. The CSC was then computed out of these resulting images. The image analysis, decision support system and automatic control of harrowing intensity by hydraulic adjustment of the tine angle were installed on a controller which was mounted on the harrow. Eight field experiments were carried out in spring cereals. Mode of harrowing intensity was changed in four experiments by speed, number of passes and tine angle. Each mode was varied in five intensities. In four experiments, only the intensity of harrowing was changed. Modes of intensity were not significantly different among each other. However, intensity had significant effects on WCE and CSC. Cereal plants recovered well from 10% CSC, and selectivity was in the constant range at 10% CSC. Therefore, 10% CSC was the threshold for the decision algorithm. If the actual CSC was below 10% CSC, intensity was increased. If the actual CSC was higher than 10%, intensity was decreased. The new system was tested in an additional field study. Threshold values for CSC were set at 10%, 30% and 60%. Automatic tine angle adjustment precisely realised the three different CSC values with variations of 1.5% to 3%. The next publication discussed and assessed the site-specific field adaptation of the development in cereals. In 2020, three field experiments were conducted in winter wheat and spring oats to investigate the response of the weed control efficacy and the crop to different harrowing intensities, in southwest Germany. In all experiments, six levels of CSC were tested. Each experiment contained an untreated control and an herbicide treatment as a comparison to the harrowing treatments. The results showed an increase in the WCE with an increasing CSC threshold. Difficult-to-control weed species such as Cirsium arvense (L.) and Galium aparine (L.) were best controlled with a CSC threshold of 70%. With a CSC threshold of 20% it was possible to control up to 98% of Thlaspi arvense (L.) The highest crop biomass, grain yield, and selectivity were achieved with an CSC threshold of 20–25% at all trial locations. With this harrowing intensity, grain yields were higher than in the herbicide control plots and a WCE of 68–98% was achieved. The last scientific article compares pairwise a conventional harrow intensity with automatic sensor-based harrowing intensity. Five field experiments in cereals were conducted at three locations in southwestern Germany in 2019 and 2020 to investigate if camera-based harrowing resulted in a more homogenous CSC and higher WCE, biomass, and crop grain yield than a conventional harrow with a constant intensity across the whole plot. For this purpose, pairwise comparisons of three fixed harrowing intensities (10 °, 40 °, and 70 ° tine angle) and three predefined CSC thresholds (CSC of 10%, 20%, and 60%) were realized in randomized complete block designs. Camera-based adjustment of the intensity resulted in 6-16% less standard deviation variation of CSC compared to fixed settings of tine angle. Crop density, WCE, crop biomass and grain yield were significantly higher for camera-based harrowing than for conventional harrowing. WCE and yields of all automatic adjusted harrowing treatments were equal to the herbicide control plots. In this PhD-thesis, a sensor-based harrow was developed and successfully investigated as an alternative to conventional herbicide application in cereals. A permanent, equal replacement of chemical weed control in arable farming systems can only be achieved using modern, sensor-based mechanical weed control approaches. Therefore, the efficacy of the mechanical weed control method can be improved and increased continuously. It has been shown that the precise adjustment of mechanical weed control methods to site-specific weed conditions allows similar WCE results as an herbicide application without causing yield losses. These findings contribute towards modern plant protection strategies to reduce the herbicide use and to establish the acceptance of technical progress in society.
Development of a spatial data infrastructure for precision agriculture applications
(2021) Jackenkroll, Markus; Gerhards, Roland
Precision agriculture (PA) is the technical answer to tackling heterogeneous conditions in a field. It works through site specific operations on a small scale and is driven by data. The objective is an optimized agricultural field application that is adaptable to local needs. The needs differ within a task by spatial conditions. A field, as a homogenous-planted unit, exceeds by its size the scale units of different landscape ecological properties, like soil type, slope, moisture content, solar radiation etc. Various PA-sensors sample data of the heterogeneous conditions in a field. PA-software and Farm Management Information Systems (FMIS) transfer the data into status information or application instructions, which are optimized for the local conditions. The starting point of the research was the determination that the process of PA was only being used in individual environments without exchange between different users and to other domains. Data have been sampled regarding specific operations, but the model of PA suffers from these closed data streams and software products. Initial sensors, data processing and controlled implementations were constructed and sold as monolithic application. An exchange of hard- or software as well as of data was not planned. The design was focused on functionality in a fixed surrounding and conceived as being a unit. This has been identified as a disadvantage for ongoing developments and the creation of added value. Influences from the outside that may be innovative or even inspired cannot be considered. To make this possible, the underlying infrastructure must be flexible and optimized for the exchange of data. This thesis explores the necessary data handling, in terms of integrating knowledge of other domains with a focus on the geo-spatial data processing. As PA is largely dependent on geographical data, this work develops spatial data infrastructure (SDI) components and is based on the methods and tools of geo-informatics. An SDI provides concepts for the organization of geospatial components. It consists of spatial- and metadata in geospatial workflows. The SDI in the center of these workflows is implemented by technologies, policies, arrangements, and interfaces to make the data accessible for various users. Data exchange is the major aim of the concept. As previously stated, data exchange is necessary for PA operations, and it can benefit from defined components of an SDI. Furthermore, PA-processes gain access to interchange with other domains. The import of additional, external data is a benefit. Simultaneously, an export interface for agricultural data offers new possibilities. Coordinated communication ensures understanding for each participant. From the technological point of view, standardized interfaces are best practice. This work demonstrates the benefit of a standardized data exchange for PA, by using the standards of the Open Geospatial Consortium (OGC). The OGC develops and publishes a wide range of relevant standards, which are widely adopted in geospatially enabled software. They are practically proven in other domains and were implemented partially in FMIS in the recent years. Depending on their focus, they could support software solutions by incorporating additional information for humans or machines into additional logics and algorithms. This work demonstrates the benefits of standardized data exchange for PA, especially by the standards of the OGC. The process of research follows five objectives: (i) to increase the usability of PA-tools in order to open the technology for a wider group of users, (ii) to include external data and services seamlessly through standardized interfaces to PA-applications, (iii) to support exchange with other domains concerning data and technology, (iv) to create a modern PA-software architecture, which allows new players and known brands to support processes in PA and to develop new business segments, (v) to use IT-technologies as a driver for agriculture and to contribute to the digitalization of agriculture.
Evaluation of weed populations under the influence of site-specific weed control to derive decision rules for a sustainable weed management
(2008) Ritter, Carina; Gerhards, Roland
In context of reduction programs for chemical plant protection, herbicide use needs to be strictly controlled and reduced to the absolute necessary extent in order to minimise negative side effects for the environment and pesticide residues in the food chain. The site specific weed management is a promising way to reduce herbicide use. It aims at managing weeds with respects to their spatial and temporal variability. Post-emergence herbicides are only applied at highly infested locations in the fields. Several studies on site-specific weed control have shown that this practice is reasonable, and it has been successfully implemented in various crops, resulting in a considerable reduction of herbicide use, treatment costs, and consequently benefits to the environment. However, there is still lack of knowledge on the population dynamics of weeds and the interactions between crop and weeds under the site-specific weed management. Long term effects of the site-specific weed control have not been studied in detail yet. Additionally, an experimental approach was needed to create precise decision algorithms for site-specific weed management. Therefore the applied scientific objective of this research was: - to analyse the spatial and temporal distribution of weeds, - to provide information on weed population dynamics under the influence of the site-specific weed control, - to detect if site-specific weed management leads to an increase in weed density, and if weed patches remain stable in density and location over time, - to determine herbicide savings and efficacy of the site specific weed management, - to design an experimental on-farm approach to explain yield variation caused by within-field heterogeneity of weed density, soil quality and herbicide application, in order to derive decision rules for site-specific weed control. During the course of this work site specific weed management tested in field trails, long term effects were examined, population dynamics were analysed and a model approach to derive management decision was approved. It was proved that weed distribution was heterogeneous in all experimental fields. The average weed density remained stable when economical weed thresholds were applied. The application of effective herbicides in every year did not reduce density in high density weed patches. The patches were persistent over eight years, with slight variations in density from year to year. It is suggested that a combination of chemical, mechanical, and cultural weed management strategies would be necessary to effectively control weeds in high density locations. However, the knowledge about the spatial stability of weed patches of individual species offers possibilities to use this information for weed management strategies. Population dynamic parameters such as weed seedling emergence, crop-weed competition, seedlings mortality, herbicide efficacy, seed production and viability were found to be weed density dependent. With increasing weed density weed biomass and fecundity increased. These findings support that weed density has to be considered in weed management strategies. Site-specific weed management was effective over time. The amount of herbicides used could be decreased significantly due to site specific herbicide application, without loosing performance. Only 26-35 % of herbicides were sprayed compared to uniform application of herbicides that is still the standard method of weed control. Additionally, a new experimental design based on an anisotropic exponential model with nugget effect was established. The influences of the co-variables weed and soil on yield and the side-effects of herbicides were quantified separately with this model, by overlaying and spatially joining all data. Out of this information, yield losses due to weed and herbicide injury could be defined, and valid decision rules for site-specific weed management could be ascertained. For the first time the injury to the crop due to herbicide application could be numeralised with this experimental design. This large loss of yield can be avoided and considerable reductions in herbicide rates can be achieved by site-specific weed management based on weed thresholds. This experimental approach enables to explain the variation of yield within agricultural fields, and an understanding of the effects on yield of the factors and their causal interactions. This work is seen as a mayor step forward in order to precisely manage weeds with respect to their spatial and temporal dynamics.
Implementation and improvement of an unmanned aircraft system for precision farming purposes
(2016) Geipel, Jakob; Claupein, Wilhelm
Precision farming (PF) is an agricultural concept that accounts for within-field variability by gathering spatial and temporal information with modern sensing technology and performs variable and targeted treatments on a smaller scale than field scale. PF research quickly recognized the possible benefits unmanned aerial vehicles (UAVs) can add to the site-specific management of farms. As UAVs are flexible carrier platforms, they can be equipped with a range of different sensing devices and used in a variety of close-range remote sensing scenarios. Most frequently, UAVs are utilized to gather actual in-season canopy information with imaging sensors that are sensitive to reflected electro-magnetic radiation in the visual (VIS) and near-infrared (NIR) spectrum. They are generally used to infer the crops’ biophysical and biochemical parameters to support farm management decisions. A current disadvantage of UAVs is that they are not designed to interact with their attached sensor payload. This leads to the need of intensive data post-processing and prohibits the possibility of real-time scenarios, in which UAVs can directly transfer information to field machinery or robots. In consequence, this thesis focused on the development of a smart unmanned aircraft system (UAS), which in the thesis’ context was regarded as a combination of a UAV carrier platform, an on-board central processing unit for sensor control and data processing, and a remotely connected ground control station. The ground control station was supposed to feature the possibility of flight mission control and the standardized distribution of sensor data with a sensor data infrastructure, serving as a data basis for a farm management information system (FMIS). The UAS was intended to be operated as a flexible monitoring tool for in-season above-ground biomass and nitrogen content estimation as well as crop yield prediction. Therefore, the selection, development, and validation of appropriate imaging sensors and processing routines were key parts to prove the UAS’ usability in PF scenarios. The individual objectives were (i) to implement an advanced UAV for PF research, providing the possibilities of remotely-controlled and automatic flight mission execution, (ii) to improve the developed UAV to a UAS by implementing sensor control, data processing and communication functionalities, (iii) to select and develop appropriate sensor systems for yield prediction and nitrogen fertilization strategies, (iv) to integrate the sensor systems into the UAS and to test the performance in example use cases, and (v) to embed the UAS into a standardized sensor data infrastructure for data storage and usage in PF applications. This work demonstrated the successful development of a custom rotary-wing UAV carrier platform with an embedded central processing unit. A modular software framework was developed with the ability to control any kind of sensor payload in real-time. The sensors can be triggered and their measurements are retrieved, fused together with the carrier’s navigation information, logged and broadcasted to a ground control station. The setup was used as basis for further research, focusing on information generation by sophisticated data processing. For a first application of predicting the grain yield of corn (Zea mays L.), a simple RGB camera was selected to acquire a set of aerial imagery of early- and mid-season corn crops. Orthoimages were processed with different ground resolutions and were computed to simple vegetation indices (VI) for a crop/non-crop classification. In addition to that, crop surface models (CSMs) were generated to estimate the crop heights. Linear regressions were performed with the corn grain yield as dependent variable and crop height and crop coverage as independent variable. The analysis showed the best prediction results of a relative root mean square error (RMSE) of 8.8 % at mid-season growth stages and ground resolutions of 4 cm px −1 . Moreover, the results indicate that with on-going canopy closure and homogeneity accounting for high ground resolutions and crop/non-crop classification becomes less and less important. For the estimation of above-ground biomass and nitrogen content in winter wheat (Triticum aestivum L.) a programmable multispectral camera was developed. It is based on an industrial multi-sensor camera, which was equipped with bandpass filters to measure four narrow wavelength bands in the so-called red-edge region. This region is the transition zone in between the VIS and NIR spectrum and known to be sensitive to leaf chlorophyll content and the structural state of the plant. It is often used to estimate biomass and nitrogen content with the help of the normalized difference vegetation index (NDVI) and the red-edge inflection point (REIP). The camera system was designed to measure ambient light conditions during the flight mission to set appropriate image acquisition times, which guarantee images with high contrast. It is fully programmable and can be further developed to a real-time image processing system. The analysis relies on semi-automatic orthoimage processing. The NDVI orthoimages were analyzed for the correlation with biomass by means of simple linear regression. These models proved to estimate biomass for all measurements with RMSEs of 12.3 % to 17.6 %. The REIP was used to infer nitrogen content and showed good results with RMSEs of 7.6 % to 11.7 %. Both NDVI and REIP were also tested for the in-season grain yield prediction ability (RMSE = 9.0–12.1 %), whereas grain protein content could be modeled with the REIP, except for low-fertilized wheat plots. The last part of the thesis comprised the development of a standardized sensor data infrastructure as a first step to a holistic farm management. The UAS was integrated into a real-time sensor data acquisition network with standardized data base storage capabilities. The infrastructure was based on open source software and the geo-data standards of the Open Geospatial Consortium (OGC). A prototype implementation was tested for four exemplary sensor systems and proved to be able to acquire, log, visualize and store the sensor data in a standardized data base via a sensor observation service on-the-fly. The setup is scalable to scenarios, where a multitude of sensors, data bases, and web services interact with each other to exchange and process data. This thesis demonstrates the successful prototype implementation of a smart UAS and a sensor data infrastructure, which offers real-time data processing functionality. The UAS is equipped with appropriate sensor systems for agricultural crop monitoring and has the potential to be used in real-world scenarios.
Mechanical weed control: Sensor-based inter-row hoeing in sugar beet (Beta vulgaris L.) in the Transylvanian depression
(2024) Parasca, Sergiu Cioca; Spaeth, Michael; Rusu, Teodor; Bogdan, Ileana
Precision agriculture is about applying solutions that serve to obtain a high yield from the optimization of resources and the development of technologies based on the collection and use of precise data. Precision agriculture, including camera-guided row detection and hydraulic steering, is often used as an alternative because crop damage can be decreased and driving speed can be increased, comparable to herbicide applications. The effects of different approaches, such as uncontrolled (UC), mechanical weed control (MWC), herbicide weed control (HWC), and mechanical + herbicide control (MWC + HWC), on weed density and yield of sugar beet were tested and evaluated in two trials (2021 and 2022) in South Transylvania Depression at the tested intervals BBCH 19 and 31. Weed control efficacy (WCE) depends on the emergence of the weeds and a good timing of weed controls in all the trials and methods, though the highest yield of sugar beet roots was recorded in the treatment MWC + HWC, with an increase up to 12–15% (56.48 t ha−1) yield from HWC (50.22 t ha−1) and a yield increase of more than 35–40% than MWC (42.34 t ha−1). Our trials show that it is possible to increase yield and have fewer chemical applications with the introduction of new precision technologies in agriculture, including sensor-guided mechanical controls.
Precision chemical weed management strategies: A review and a design of a new CNN-based modular spot sprayer
(2022) Allmendinger, Alicia; Spaeth, Michael; Saile, Marcus; Peteinatos, Gerassimos G.; Gerhards, Roland
Site-specific weed control offers a great potential for herbicide savings in agricultural crops without causing yield losses and additional weed management costs in the following years. Therefore, precision weed management is an efficient tool to meet the EU targets for pesticide reduction. This review summarizes different commercial technologies and prototypes for precision patch spraying and spot spraying. All the presented technologies have in common that they consist of three essential parts. (1) Sensors and classifiers for weed/crop detection, (2) Decision algorithms to decide whether weed control is needed and to determine a suitable type and rate of herbicide. Usually, decision algorithms are installed on a controller and (3) a precise sprayer with boom section control or single nozzle control. One point that differs between some of the techniques is the way the decision algorithms classify. They are based on different approaches. Green vegetation can be differentiated from soil and crop residues based on spectral information in the visible and near-infrared wavebands (“Green on Brown”). Those sensors can be applied for real-time on/off control of single nozzles to control weeds before sowing after conservation tillage and in the inter-row area of crops. More sophisticated imaging algorithms are used to classify weeds in crops (“Green on Green”). This paper will focus on Convolutional Neural Networks (CNN) for plant species identification. Alternatively, the position of each crop can be recorded during sowing/planting and afterward herbicides can be targeted to single weeds or larger patches of weeds if the economic weed threshold is exceeded. With a standardized protocol of data communication between sensor, controller and sprayer, the user can combine different sensors with different sprayers. In this review, an ISOBUS communication protocol is presented for a spot sprayer. Precision chemical weed control can be realized with tractor-mounted sprayers and autonomous robots. Commercial systems for both classes will be introduced and their economic and environmental benefits and limitations will be highlighted. Farmers ask for robust systems with less need for maintenance and flexible application in different crops.
Spatial combination of sensor data deriving from mobile platforms for precision farming applications
(2019) Zecha, Christoph Walter; Gerhards, Roland
This thesis combines optical sensors on a ground and on an aerial platform for field measurements in wheat, to identify nitrogen (N) levels, estimating biomass (BM) and predicting yield. The Multiplex Research (MP) fluorescence sensor was used for the first time in wheat. The individual objectives were: (i) Evaluation of different available sensors and sensor platforms used in Precision Farming (PF) to quantify the crop nutrition status, (ii) Acquisition of ground and aerial sensor data with two ground spectrometers, an aerial spectrometer and a ground fluorescence sensor, (iii) Development of effective post-processing methods for correction of the sensor data, (iv) Analysis and evaluation of the sensors with regard to the mapping of biomass, yield and nitrogen content in the plant, and (v) Yield simulation as a function of different sensor signals. This thesis contains three papers, published in international peer-reviewed journals. The first publication is a literature review on sensor platforms used in agricultural research. A subdivision of sensors and their applications was done, based on a detailed categorization model. It evaluates strengths and weaknesses, and discusses research results gathered with aerial and ground platforms with different sensors. Also, autonomous robots and swarm technologies suitable for PF tasks were reviewed. The second publication focuses on spectral and fluorescence sensors for BM, yield and N detection. The ground sensors were mounted on the Hohenheim research sensor platform “Sensicle”. A further spectrometer was installed in a fixed-wing Unmanned Aerial Vehicle (UAV). In this study, the sensors of the Sensicle and the UAV were used to determine plant characteristics and yield of three-year field trials at the research station Ihinger Hof, Renningen (Germany), an institution of the University of Hohenheim, Stuttgart (Germany). Winter wheat (Triticum aestivum L.) was sown on three research fields, with different N levels applied to each field. The measurements in the field were geo-referenced and logged with an absolute GPS accuracy of ±2.5 cm. The GPS data of the UAV was corrected based on the pitch and roll position of the UAV at each measurement. In the first step of the data analysis, raw data obtained from the sensors was post-processed and was converted into indices and ratios relating to plant characteristics. The converted ground sensor data were analysed, and the results of the correlations were interpreted related to the dependent variables (DV) BM weight, wheat yield and available N. The results showed significant positive correlations between the DV’s and the Sensicle sensor data. For the third paper, the UAV sensor data was included into the evaluations. The UAV data analysis revealed low significant results for only one field in the year 2011. A multirotor UAV was considered as a more viable aerial platform, that allows for more precision and higher payload. Thereby, the ground sensors showed their strength at a close measuring distance to the plant and a smaller measurement footprint. The results of the two ground spectrometers showed significant positive correlations between yield and the indices from CropSpec, NDVI (Normalised Difference Vegetation Index) and REIP (Red-Edge Inflection Point). Also, FERARI and SFR (Simple Fluorescence Ratio) of the MP fluorescence sensor were chosen for the yield prediction model analysis. With the available N, CropSpec and REIP correlated significantly. The BM weight correlated with REIP even at a very early growing stage (Z 31), and with SAVI (Soil-Adjusted Vegetation Index) at ripening stage (Z 85). REIP, FERARI and SFR showed high correlations to the available N, especially in June and July. The ratios and signals of the MP sensor were highly significant compared to the BM weight above Z 85. Both ground spectrometers are suitable for data comparison and data combination with the active MP fluorescence sensor. Through a combination of fluorescence ratios and spectrometer indices, linear models for the prediction of wheat yield were generated, correlating significantly over the course of the vegetative period for research field Lammwirt (LW) in 2012. The best model for field LW in 2012 was selected for cross-validation with the measurements of the fields Inneres Täle (IT) and Riech (RI) in 2011 and 2012. However, it was not significant. By exchanging only one spectral index with a fluorescence ratio in a similar linear model, it showed significant correlations. This work successfully proves the combination of different sensor ratios and indices for the detection of plant characteristics, offering better and more robust predictions and quantifications of field parameters without employing destructive methods. The MP sensor proved to be universally applicable, showing significant correlations to the investigated characteristics such as BM weight, wheat yield and available N.