Comparison between artificial neural networks and maximum likelihood classification in digital soil mapping

Soil surveys are the main source of spatial information on soils and have a range of different applications, mainly in agriculture. The continuity of this activity has however been severely compromised, mainly due to a lack of governmental funding. The purpose of this study was to evaluate the feasibility of two different classifiers (artificial neural networks and a maximum likelihood algorithm) in the prediction of soil classes in the northwest of the state of Rio de Janeiro. Terrain attributes such as elevation, slope, aspect, plan curvature and compound topographic index (CTI) and indices of clay minerals, iron oxide and Normalized Difference Vegetation Index (NDVI), derived from Landsat 7 ETM+ sensor imagery, were used as discriminating variables. The two classifiers were trained and validated for each soil class using 300 and 150 samples respectively, representing the characteristics of these classes in terms of the discriminating variables. According to the statistical tests, the accuracy of the classifier based on artificial neural networks (ANNs) was greater than of the classic Maximum Likelihood Classifier (MLC). Comparing the results with 126 points of reference showed that the resulting ANN map (73.81 %) was superior to the MLC map (57.94 %). The main errors when using the two classifiers were caused by: a) the geological heterogeneity of the area coupled with problems related to the geological map; b) the depth of lithic contact and/or rock exposure, and c) problems with the environmental correlation model used due to the polygenetic nature of the soils. This study confirms that the use of terrain attributes together with remote sensing data by an ANN approach can be a tool to facilitate soil mapping in Brazil, primarily due to the availability of low-cost remote sensing data and the ease by which terrain attributes can be obtained.

Building predictive models of soil particle-size distribution

Is it possible to build predictive models (PMs) of soil particle-size distribution (psd) in a region with complex geology and a young and unstable land-surface? The main objective of this study was to answer this question. A set of 339 soil samples from a small slope catchment in Southern Brazil was used to build PMs of psd in the surface soil layer. Multiple linear regression models were constructed using terrain attributes (elevation, slope, catchment area, convergence index, and topographic wetness index). The PMs explained more than half of the data variance. This performance is similar to (or even better than) that of the conventional soil mapping approach. For some size fractions, the PM performance can reach 70 %. Largest uncertainties were observed in geologically more complex areas. Therefore, significant improvements in the predictions can only be achieved if accurate geological data is made available. Meanwhile, PMs built on terrain attributes are efficient in predicting the particle-size distribution (psd) of soils in regions of complex geology.

Comparison between detailed digital and conventional soil maps of an area with complex geology

Since different pedologists will draw different soil maps of a same area, it is important to compare the differences between mapping by specialists and mapping techniques, as for example currently intensively discussed Digital Soil Mapping. Four detailed soil maps (scale 1:10.000) of a 182-ha sugarcane farm in the county of Rafard, São Paulo State, Brazil, were compared. The area has a large variation of soil formation factors. The maps were drawn independently by four soil scientists and compared with a fifth map obtained by a digital soil mapping technique. All pedologists were given the same set of information. As many field expeditions and soil pits as required by each surveyor were provided to define the mapping units (MUs). For the Digital Soil Map (DSM), spectral data were extracted from Landsat 5 Thematic Mapper (TM) imagery as well as six terrain attributes from the topographic map of the area. These data were summarized by principal component analysis to generate the map designs of groups through Fuzzy K-means clustering. Field observations were made to identify the soils in the MUs and classify them according to the Brazilian Soil Classification System (BSCS). To compare the conventional and digital (DSM) soil maps, they were crossed pairwise to generate confusion matrices that were mapped. The categorical analysis at each classification level of the BSCS showed that the agreement between the maps decreased towards the lower levels of classification and the great influence of the surveyor on both the mapping and definition of MUs in the soil map. The average correspondence between the conventional and DSM maps was similar. Therefore, the method used to obtain the DSM yielded similar results to those obtained by the conventional technique, while providing additional information about the landscape of each soil, useful for applications in future surveys of similar areas.

Physical quality of an Oxisol after different periods of management systems

Management systems may lead to a loss of soil physical quality as a result of removal of the plant cover and excessive agricultural mechanization. The hypothesis of this study was that the soil aggregate stability, bulk density, macro- and microporosity, and the S index and saturated hydraulic conductivity may be used as indicators of the soil physical quality. The aim was to study the effects of different periods and managements on the physical attributes of a medium-textured Red Oxisol under soybean and corn for two growing seasons, and determine which layers are most susceptible to variations. A completely randomized experimental design was used with split plots (five treatments and four layers), with four replications. The treatments in 2008/09 consisted of: five years of no-tillage (NTS5), seven years of no-tillage (NTS7), nine years of no-tillage (NTS9), conventional tillage (CTS) and an adjacent area of native forest (NF). The treatments were extended for another year, identified in 2009/10 as: NTS6, NTS8, NTS10, CTS and NF. The soil layers 0-0.05, 0.05-0.10, 0.10-0.20 and 0.20-0.30 m were sampled. The highest S index values were observed in the treatment CTS in the 0-0.05 m layer (0.106) and the 0.05-0.10 m layer (0.099) in 2008/09, and in the 0-0.05 m layer (0.066) in 2009/10. This fact may be associated with soil turnover, resulting in high macroporosity in this treatment. In contrast, in the NTS, limiting macroporosity values were observed in some layers (below 0.10 m³ m-3). Highest aggregate stability as well as the highest saturated hydraulic conductivity (Kθ) values were observed in NF in relation to the other treatments. In 2009/10, the Kθ in NF differed only from NTS10. This study showed that the use of the S index alone cannot be recommended as an absolute indicator of the soil physical quality, even at values greater than 0.035.

Quality of surface water related to land use: a case study in a catchment with small farms and intensive vegetable crop production in southern Brazil

Water degradation is strongly related to agricultural activity. The aim of this study was to evaluate the influence of land use and some environmental components on surface water quality in the Campestre catchment, located in Colombo, state of Parana, Brazil. Physical and chemical attributes were analyzed (total nitrogen, ammonium, nitrate, total phosphorus, electrical conductivity, pH, temperature, turbidity, total solids, biological oxygen demand, chemical oxygen demand and dissolved oxygen). Monthly samples of the river water were taken over one year at eight monitoring sites, distributed over three sub-basins. Overall, water quality was worse in the sub-basin with a higher percentage of agriculture, and was also affected by a lower percentage of native forest and permanent preservation area, and a larger drainage area. Water quality was also negatively affected by the presence of agriculture in the riparian zone. In the summer season, probably due to higher rainfall and intensive soil use, a higher concentration of total nitrogen and particulate nitrogen was observed, as well as higher electrical conductivity, pH and turbidity. All attributes, except for total phosphorus, were in compliance with Brazilian Conama Resolution Nº 357/2005 for freshwater class 1. However, it should be noted that these results referred to the base flow and did not represent a discharge condition since most of the water samples were not collected at or near the rainfall event.

Artificial neural networks applied for soil class prediction in mountainous landscape of the Serra do Mar¹

Soil information is needed for managing the agricultural environment. The aim of this study was to apply artificial neural networks (ANNs) for the prediction of soil classes using orbital remote sensing products, terrain attributes derived from a digital elevation model and local geology information as data sources. This approach to digital soil mapping was evaluated in an area with a high degree of lithologic diversity in the Serra do Mar. The neural network simulator used in this study was JavaNNS and the backpropagation learning algorithm. For soil class prediction, different combinations of the selected discriminant variables were tested: elevation, declivity, aspect, curvature, curvature plan, curvature profile, topographic index, solar radiation, LS topographic factor, local geology information, and clay mineral indices, iron oxides and the normalized difference vegetation index (NDVI) derived from an image of a Landsat-7 Enhanced Thematic Mapper Plus (ETM+) sensor. With the tested sets, best results were obtained when all discriminant variables were associated with geological information (overall accuracy 93.2 - 95.6 %, Kappa index 0.924 - 0.951, for set 13). Excluding the variable profile curvature (set 12), overall accuracy ranged from 93.9 to 95.4 % and the Kappa index from 0.932 to 0.948. The maps based on the neural network classifier were consistent and similar to conventional soil maps drawn for the study area, although with more spatial details. The results show the potential of ANNs for soil class prediction in mountainous areas with lithological diversity.

SOIL CHEMICAL PROPERTIES AND GROWTH OF SUNFLOWER (HELIANTHUS ANNUUS L.) AS AFFECTED BY THE APPLICATION OF ORGANIC FERTILIZERS AND INOCULATION WITH ARBUSCULAR MYCORRHIZAL FUNGI

The use of organic fertilizers and the inoculation of mycorrhizal fungi in the cultivation of oil crops is essential to reduce production costs and minimize negative impacts on natural resources. A field experiment was conducted in an Argissolo Amarelo (Ultisol) with the aim of evaluating the effects of fertilizer application and inoculation of arbuscular mycorrhizal fungi on the growth attributes of sunflower (Helianthus annuus L.) and on soil chemical properties. The experiment was conducted at the Federal University of Rio Grande do Norte, Brazil, using a randomized block design with three replicates in a 4 × 2 factorial arrangement consisting of four treatments in regard to application of organic fertilizer (liquid biofertilizer, cow urine, mineral fertilizer, and unfertilized control) and two treatments in regard to arbuscular mycorrhizal fungi (with and without mycorrhizal fungi). The results showed that the physiological attributes of relative growth rate and leaf weight ratio were positively influenced by fertilization, compared to the control treatment, likely brought about by the supply of nutrients from the fertilizers applied. The growth and productivity attributes were positively affected by mycorrhization.

Multiple Geotechnological Tools Applied to Digital Mapping of Tropical Soils

ABSTRACT In recent years, geotechnologies as remote and proximal sensing and attributes derived from digital terrain elevation models indicated to be very useful for the description of soil variability. However, these information sources are rarely used together. Therefore, a methodology for assessing and specialize soil classes using the information obtained from remote/proximal sensing, GIS and technical knowledge has been applied and evaluated. Two areas of study, in the State of São Paulo, Brazil, totaling approximately 28.000 ha were used for this work. First, in an area (area 1), conventional pedological mapping was done and from the soil classes found patterns were obtained with the following information: a) spectral information (forms of features and absorption intensity of spectral curves with 350 wavelengths -2,500 nm) of soil samples collected at specific points in the area (according to each soil type); b) obtaining equations for determining chemical and physical properties of the soil from the relationship between the results obtained in the laboratory by the conventional method, the levels of chemical and physical attributes with the spectral data; c) supervised classification of Landsat TM 5 images, in order to detect changes in the size of the soil particles (soil texture); d) relationship between classes relief soils and attributes. Subsequently, the obtained patterns were applied in area 2 obtain pedological classification of soils, but in GIS (ArcGIS). Finally, we developed a conventional pedological mapping in area 2 to which was compared with a digital map, ie the one obtained only with pre certain standards. The proposed methodology had a 79 % accuracy in the first categorical level of Soil Classification System, 60 % accuracy in the second category level and became less useful in the categorical level 3 (37 % accuracy).

Planosols Developed in Different Geoenvironmental Conditions in Northeastern Brazil

ABSTRACT The semiarid region of northeastern Brazil has a large area occupied by Planosols, where in the State of Pernambuco these soils are mainly used for livestock farming and subsistence crops. The knowledge on these soils is limited, which compromises the understanding on their behavior, potentialities and limitations.This study aimed to analyze morphological, chemical, physical and mineralogical attributes of Planosols developed under different geoenvironmental conditions. Morphological descriptions and chemical, physical and mineralogical analyses were performed in four profiles of Planosols along a rainfall gradient. An increase in rainfall allowed for an increase in the clay content in the Bt horizon and a reduction in ESP, EC, Na+, CEC, S, pH (water and KCl) and soil density. Horizons A and E were thicker in Planosols in more humid environments. The increase in ESP associated with the presence of expansive minerals (smectite and vermiculite) allowed the development of a prismatic structure in Haplic Planosols and a columnar structure in Natric Planosols. The mineralogical assembly is indicative of poorly weathered soils. The mineralogical assemblies of the silt and clay fractions were similar in the different geoenvironments, while higher contents of easily alterable minerals were observed in the composition of the sand fraction in environments with a drier climate.

Boron adsorption in soils from the State of São Paulo, Brazil

Boron adsorption was studied in five representative soils (Rhodic Hapludox, Arenic Paleudalf and three Typic Hapludox) from the State of São Paulo, Brazil. Adsorption was higher in the clayey Oxisols, followed by the Alfisol and the coarser Oxisols. Calcium carbonate promoted an increase in the amount of adsorbed boron in all soils, with the most pronounced effect in the coarser-textured Oxisols. High correlation coefficients were found between adsorbed boron and clay and amorphous aluminum oxide contents and specific surface area (r = 0.79, 0.76 and 0.73, respectively, p < 0.01). Clay content, free aluminum oxide, and hot CaCl2 (0.01 mol L-1)-extracted boron explained 93% of the variation of adsorbed boron. Langmuir and Freundlich isotherms fitted well to the adsorbed data, and highest values for maximum boron adsorption were found in clayey soils, which were significantly correlated with contents of total, free and amorphous iron and aluminum oxides, as well with the physical attributes. Ninety four percent of the variation in the maximum adsorption could be related to the free iron content.

Yield and fruit quality of apple from conventional and organic production systems

The objective of this study was to assess the yield and fruit quality of apple produced with a conventional and an organic production systems in Southern Brazil. The orchards consisted of alternate rows from 10 to 12-year old 'Royal Gala' and 'Fuji' apple trees on M.7 rootstocks, grown as slender spindles, on 4x6 m spacing. Eighteen apple trees of each cultivar and management system were randomly selected and assessed for nutrition, flowering, fruit set, yield, and fruit quality during two growing seasons (2002/2003 and 2003/2004). The organic management system resulted in lower concentrations of K, Mg, and N in leaves and fruits, and in smaller fruits for both cultivars, and lower fruit yield for 'Fuji' than from the conventional production system. For both cultivars, fruits from the organic orchard harvested at commercial maturity had a more yellowish skin background color, higher percentage of blush in the fruit skin, higher soluble solids content, higher density, higher flesh firmness, and higher severity of russet than fruits from the conventional orchard. Fruit from the organic orchard had lower titratable acidity in 'Royal Gala', and higher incidence of moldy core and lower incidence of watercore in 'Fuji', than fruit from the conventional orchard. A non-trained sensory panel detected no significant differences for fruit attributes of taste, flavor and texture between fruit from the production systems for either cultivar.

Yield and mineral nutrition of soybean, maize, and Congo signal grass as affected by limestone and slag

The objective of this work was to evaluate the efficiency of superficial application of limestone and slag, and their effects on soil chemical attributes and on yield and mineral nutrition of soybean, maize, and Congo signal grass (Urochloa ruziziensis). The experiment was carried out in a Rhodic Hapludox under no tillage system. The treatments consisted of the use of limestone or slag (silicates of calcium and magnesium) to correct soil acidity, and of a control treatment without the use of soil correctives. Rates were calculated in order to raise soil base saturation up to 70%. Soybean was sown in November 2006 and maize in December 2007. Congo signal grass was sown right after the harvests of soybean and maize, and it was cropped during the off-seasons. Soil chemical attributes were evaluated at 6, 12, and 18 months after the application of the corrective materials. Slag is an efficient source for soil acidity correction, being able to raise the exchangeable base levels in the soil profile faster than lime. Both limestone and slag increase dry matter yield of Congo signal grass, and grain yield of soybean and maize. Slag is more effective in improving maize grain yield.

Shelf life and sensory assessment of tilapia quenelle during frozen storage

The objective of this work was to evaluate the shelf life and sensory attributes of tilapia quenelle. Treatments consisted of two types of packages - polyethylene zipper (retort pouch) (QA) and polyethylene waxed paper box (QB) - stored at -18ºC for 120 days. Tilapia quenelle was stable for all parameters established by Brazilian legislation. Average values of the evaluated attributes in different packages, during storage, showed no significant difference, except for the "refrigeration" flavor. However, during the storage period, there were significant differences for sensory attributes, as "moist appearance", fish and product aroma, and off flavors of "mud" and "refrigeration". Preserving product quality as for its sensory attributes, during storage, shows that tilapia quenelle is a convenience product and contributes to the increase of fish consumption.

The ideal table grapes for the Spanish market

This paper seeks to explore a survey of consumers in Spain. The survey explores the attributes of quality that consumers are seeking and promotion of grapes via "quality" marks, which are indicators of possible ways to increase demand. The reason consumers are switching to other foods, such as dairy based snacks, is that grapes are not easy to eat, can be unreliable in terms of their quality attributes, and their price more variable. Consumers are also generally unaware of the marks quality currently used.

Addition of nitrogen had no effect on yield and quality of apples in an high density orchard carrying a dwarf rootstock

The effect of N addition on apple yield and quality may vary according to the tree vigor. Apple trees developed over vigorous rootstocks had shown no response to N application in Brazil. In this study it was evaluated the effect of N addition to the soil on yield and quality of ´Royal Gala´ apples grafted on a dwarf rootstock (M.9). The orchard was planted in 1995 (2,857 trees ha-1) on an Oxisol containing 40 g kg-1 of organic matter and pH 6.0. The experiment was carried out from 1998 up to 2005. Treatments consisted of rates of N (0, 50, 100 and 150 kg ha-1 year-1 from 1998 to 2001, and respectively 0, 100, 200 and 300 kg ha-1 afterwards), all broadcasted within the tree row in two equal splits, at bud break and after harvest, as ammonium sulfate. Addition of N to the soil had no effect on fruit yield over the six years regardless of the applied rate. Averaged across treatments and years, fruit yield was 52.3 t ha-1. Nitrogen in the leaves (average of 24 g kg-1) or in the fruits (average of 346 mg kg-1) as well as some attributes related to fruit quality (color, firmness, acidity, soluble solids, physiological disorders) were unaffected by N addition. Some plant parameters related to tree vigor, however, grew higher with the increase on N rate. Thus, it is not necessary to apply N to deep Brazilian soils containing high organic matter in order to assure good fruit quality and yield on high-density orchards carrying dwarf rootstocks probably because the N required for tree growth and fruit production is supplied from soil organic matter decay.