Automatic expert system based on images for accuracy crop row detection in maize fields

This paper proposes an automatic expert system for accuracy crop row detection in maize fields based on images acquired from a vision system. Different applications in maize, particularly those based on site specific treatments, require the identification of the crop rows. The vision system is designed with a defined geometry and installed onboard a mobile agricultural vehicle, i.e. submitted to vibrations, gyros or uncontrolled movements. Crop rows can be estimated by applying geometrical parameters under image perspective projection. Because of the above undesired effects, most often, the estimation results inaccurate as compared to the real crop rows. The proposed expert system exploits the human knowledge which is mapped into two modules based on image processing techniques. The first one is intended for separating green plants (crops and weeds) from the rest (soil, stones and others). The second one is based on the system geometry where the expected crop lines are mapped onto the image and then a correction is applied through the well-tested and robust Theil–Sen estimator in order to adjust them to the real ones. Its performance is favorably compared against the classical Pearson product–moment correlation coefficient.

Discriminating Crop, Weeds and Soil Surface with a Terrestrial LIDAR Sensor

In this study, the evaluation of the accuracy and performance of a light detection and ranging (LIDAR) sensor for vegetation using distance and reflection measurements aiming to detect and discriminate maize plants and weeds from soil surface was done. The study continues a previous work carried out in a maize field in Spain with a LIDAR sensor using exclusively one index, the height profile. The current system uses a combination of the two mentioned indexes. The experiment was carried out in a maize field at growth stage 12–14, at 16 different locations selected to represent the widest possible density of three weeds: Echinochloa crus-galli (L.) P.Beauv., Lamium purpureum L., Galium aparine L.and Veronica persica Poir.. A terrestrial LIDAR sensor was mounted on a tripod pointing to the inter-row area, with its horizontal axis and the field of view pointing vertically downwards to the ground, scanning a vertical plane with the potential presence of vegetation. Immediately after the LIDAR data acquisition (distances and reflection measurements), actual heights of plants were estimated using an appropriate methodology. For that purpose, digital images were taken of each sampled area. Data showed a high correlation between LIDAR measured height and actual plant heights (R 2 = 0.75). Binary logistic regression between weed presence/absence and the sensor readings (LIDAR height and reflection values) was used to validate the accuracy of the sensor. This permitted the discrimination of vegetation from the ground with an accuracy of up to 95%. In addition, a Canonical Discrimination Analysis (CDA) was able to discriminate mostly between soil and vegetation and, to a far lesser extent, between crop and weeds. The studied methodology arises as a good system for weed detection, which in combination with other principles, such as vision-based technologies, could improve the efficiency and accuracy of herbicide spraying.

Crop rotation and residues influence N2O emission and N efficiency rather than tillage under a rainfed Mediterranean agroecosystem

Conservation tillage and crop rotation have spread during the last decades because promotes several positive effects (increase of soil organic content, reduction of soil erosion, and enhancement of carbon sequestration) (Six et al., 2004). However, these benefits could be partly counterbalanced by negative effects on the release of nitrous oxide (N2O) (Linn and Doran, 1984). There is a lack of data on long-term tillage system study, particularly in Mediterranean agro-ecosystems. The aim of this study was to evaluate the effects of long-term (>17 year) tillage systems (no tillage (NT), minimum tillage (MT) and conventional tillage (CT)); and crop rotation (wheat (W)-vetch (V)-barley (B)) versus wheat monoculture (M) on N2O emissions. Additionally, Yield-scaled N2O emissions (YSNE) and N uptake efficiency (NUpE) were assessed for each treatment.

Influence of Tillage and Liming on N2O emission from a rainfed crop

Nitrous oxide (N2O) is the main greenhouse gas (GHG) produced by agricultural soils due to microbial processes. The application of N fertilizers is associated with an increase of N2O losses. However, it is possible to mitigate these emissions by the introduction of adequate management practices (Snyder et al., 2009). Soil conservation practices (i.e.no tillage, NT) have recently become widespread because they promote several positive effects (increases in soil organic carbonand soil fertility, reduction of soil erosion, etc). In terms of GHG emissions, there is no consensus in the literature on the effects of tillage on N2O. Several studies found that NT can produce greater (Baggs et al., 2003), lower (Malhi et al., 2006) or similar (Grandey et al., 2006) N2O emissions compared to traditional tillage (TT). This large uncertainty is associated with the duration of tillage practices and climatic variability. Liming is widely use to solve problems of soil acidity (Al toxicity, yield penalties, etc). Several studies show a decrease in N2O emissions with liming (Barton et al., 2013) whereas no significant effects or increases were observed in others (Galbally et al., 2010). The aim of this work was to evaluate the effects of tillage (NT vs TT) and liming application or not of Ca-amendment) on N2O emissions from an acid soil during a rainfed crop.

Soil P and cation availability and crop uptake in a forage rotation under conventional and reduced tillage

Long-term conservation tillage can modify vertical distribution of nutrients in soil profiles and alter nutrient availability and yields of crops.

How can irrigated agriculture adapt to climate change? Insights from the Guadiana Basin in Spain

Climate change is already affecting many natural systems and human environments worldwide, like the semiarid Guadiana Basin in Spain. This paper illustrates a systematic analysis of climate change adaptation in the Guadiana irrigation farming region. The study applies a solution-oriented diagnostic framework structured along a series of sequential analytical steps. An initial stage integrates economic and hydrologic modeling to evaluate the effects of climate change on the agriculture and water sectors. Next, adaptation measures are identified and prioritized through a stakeholder-based multi-criteria analysis. Finally, a social network analysis identifies key actors and their relationships in climate change adaptation. The study shows that under a severe climate change scenario, water availability could be substantially decreased and drought occurrence will augment. In consequence, farmers will adapt their crops to a lesser amount of water and income gains will diminish, particularly for smallholder farms. Among the various adaptation measures considered, those related to private farming (new crop varieties and modern irrigation technologies) are ranked highest, whereas public-funded hard measures (reservoirs) are lowest and public soft measures (insurance) are ranked middle. In addition, stakeholders highlighted that the most relevant criteria for selecting adaptation plans are environmental protection, financial feasibility and employment creation. Nonetheless, the social network analysis evidenced the need to strengthen the links among the different stakeholder groups to facilitate the implementation of adaptation processes. In sum, the diagnostic framework applied in this research can be considered a valuable tool for guiding and supporting decision making in climate change adaptation and communicating scientific results.

Efficiency and environmental indexes to evaluate the sustainability of mineral and organic fertilization in an irrigated melon crop

Melon is traditionally cultivated in fertigated farmlands in the center of Spain with high inputs of water and N fertilizer. Excess N can have a negative impact, from the economic point of view, since it can diminish the production and quality of the fruit, from the environmental point of view, since it is a very mobile element in the soil and can contaminate groundwater. From health point of view, nitrate can be accumulated in fruit pulp, and, in addition, groundwater is the fundamental supply source of human populations. Best management practices are particularly necessary in this region as many zones have been declared vulnerable to NO3- pollution (Directive 91/676/CEE) During successive years, a melon crop (Cucumis melo L.) was grown under field conditions applying mineral and organic fertilizers under drip irrigation. Different doses of ammonium nitrate were used as well as compost derived from the wine-distillery industry which is relevant in this area. The present study reviews the most common N efficiency indexes under the different management options with a view to maximizing yield and minimizing N loss.

Yield, nutrient utilization and soil properties in a melon crop amended with wine-distillery waste

In Spain, large quantities of wine are produced every year (3,339,700 tonnes in 2011) (FAO, 2011) with the consequent waste generation. During the winemaking process, solid residues like grape stalks are generated, as well as grape marc and wine lees as by-products. According to the Council Regulation (EC) 1493/1999 on the common organization of the wine market, by-products coming from the winery industry must be sent to alcohol-distilleries to generate exhausted grape marc and vinasses. With an adequate composting treatment, these wastes can be applied to soils as a source of nutrients and organic matter. A three-year field experiment (2011, 2012 and 2013) was carried out in Ciudad Real (central Spain) to study the effects of wine-distillery waste compost application in a melon crop (Cucumis melo L.). Melon crop has been traditionally cultivated in this area with high inputs of water and fertilizers, but no antecedents of application of winery wastes are known. In a randomized complete block design, four treatments were compared: three compost doses consisted of 6.7 (D1), 13.3 (D2) and 20 t compost ha-1 (D3), and a control treatment without compost addition (D0). The soil was a shallow sandy-loam (Petrocalcic Palexeralfs) with a depth of 0.60 m and a discontinuous petrocalcic horizon between 0.60 and 0.70 m, slightly basic (pH 8.4), poor in organic matter (0.24%), rich in potassium (410 ppm) and with a medium level of phosphorus (22.1 ppm). During each growing period four harvests were carried out and total and marketable yield (fruits weighting <1 kg or visually rotten were not considered), fruit average weight and fruit number per plant were determined. At the end of the crop cycle, four plants per treatment were sampled and the nutrient content (N, P and K) was determined. Soil samplings (0-30 cm depth) were carried before the application of compost and at the end of each growing season and available N and P, as well as exchangeable K content were analyzed. With this information, an integrated analysis was carried out with the aim to evaluate the suitability of this compost as organic amendment.

Ground and airborne level optical sensors: is it possible to estimate maize crop N status?

Adjusting N fertilizer application to crop requirements is a key issue to improve fertilizer efficiency, reducing unnecessary input costs to farmers and N environmental impact. Among the multiple soil and crop tests developed, optical sensors that detect crop N nutritional status may have a large potential to adjust N fertilizer recommendation (Samborski et al. 2009). Optical readings are rapid to take and non-destructive, they can be efficiently processed and combined to obtain indexes or indicators of crop status. However, other physiological stress conditions may interfere with the readings and detection of the best crop nutritional status indicators is not always and easy task. Comparison of different equipments and technologies might help to identify strengths and weakness of the application of optical sensors for N fertilizer recommendation. The aim of this study was to evaluate the potential of various ground-level optical sensors and narrow-band indices obtained from airborne hyperspectral images as tools for maize N fertilizer recommendations. Specific objectives were i) to determine which indices could detect differences in maize plants treated with different N fertilizer rates, and ii) to evaluate its ability to identify N-responsive from non-responsive sites.

The impact of large-scale circulation patterns on summer crop in Iberian Peninsula

Large-scale circulations patterns (ENSO, NAO) have been shown to have a significant impact on seasonal weather, and therefore on crop yield over many parts of the world(Garnett and Khandekar, 1992; Aasa et al., 2004; Rozas and Garcia-Gonzalez, 2012). In this study, we analyze the influence of large-scale circulation patterns and regional climate on the principal components of maize yield variability in Iberian Peninsula (IP) using reanalysis datasets. Additionally, we investigate the modulation of these relationships by multidecadal patterns. This study is performed analyzing long time series of maize yield, only climate dependent, computed with the crop model CERES-maize (Jones and Kiniry, 1986) included in Decision Support System for Agrotechnology Transfer (DSSAT v.4.5).

Examining wheat yield sensitivity to temperature and precipitation changes for a large ensemble of crop models using impact response surfaces

Impact response surfaces (IRSs) depict the response of an impact variable to changes in two explanatory variables as a plotted surface. Here, IRSs of spring and winter wheat yields were constructed from a 25-member ensemble of process-based crop simulation models. Twenty-one models were calibrated by different groups using a common set of calibration data, with calibrations applied independently to the same models in three cases. The sensitivity of modelled yield to changes in temperature and precipitation was tested by systematically modifying values of 1981-2010 baseline weather data to span the range of 19 changes projected for the late 21st century at three locations in Europe.

Designing new cereal cultivars as an adaptation measure using crop model ensembles

To date, crop models have been little used for characterising the types of cultivars suited to a changed climate, though simulations of altered management (e.g. sowing) are often reported. However, in neither case are model uncertainties evaluated at the same time.

Improving Crop Models: Incorporating New Processes, New Approaches, and Better Calibrations

Early ancestors of crop simulation models (De Wit, 1965; Monteith, 1965; Duncan et al., 1967) were born before primitive personal computers were available (e.g. Apple II released in 1977, IBM PC released in 1981). Paleo-computer programs were run in mainframes with the support of punch cards. As computers became more available and powerful, crop models evolved into sophisticated tools summarizing our understanding of how crops operate. This evolution was triggered by the need to answer new scientific questions and improve the accuracy of model simulations, especially under limiting conditions.

Model inter-comparison on crop rotation effects ? an intermediate report

Data of diverse crop rotations from five locations across Europe were distributed to modelers to investigate the capability of models to handle complex crop rotations and management interactions.

Testing of crop Models for Accurate Predictions of Evapotranspiration and crop Water Use

All crop models, whether site-specific or global-gridded and regardless of crop, simulate daily crop transpiration and soil evaporation during the crop life cycle, resulting in seasonal crop water use. Modelers use several methods for predicting daily potential evapotranspiration (ET), including FAO-56, Penman-Monteith, Priestley-Taylor, Hargreaves, full energy balance, and transpiration water efficiency. They use extinction equations to partition energy to soil evaporation or transpiration, depending on leaf area index. Most models simulate soil water balance and soil-root water supply for transpiration, and limit transpiration if water uptake is insufficient, and thereafter reduce dry matter production. Comparisons among multiple crop and global gridded models in the Agricultural Model Intercomparison and Improvement Project (AgMIP) show surprisingly large differences in simulated ET and crop water use for the same climatic conditions. Model intercomparisons alone are not enough to know which approaches are correct. There is an urgent need to test these models against field-observed data on ET and crop water use. It is important to test various ET modules/equations in a model platform where other aspects such as soil water balance and rooting are held constant, to avoid compensation caused by other parts of models. The CSM-CROPGRO model in DSSAT already has ET equations for Priestley-Taylor, Penman-FAO-24, Penman-Monteith-FAO-56, and an hourly energy balance approach. In this work, we added transpiration-efficiency modules to DSSAT and AgMaize models and tested the various ET equations against available data on ET, soil water balance, and season-long crop water use of soybean, fababean, maize, and other crops where runoff and deep percolation were known or zero. The different ET modules created considerable differences in predicted ET, growth, and yield.