Influence of data preprocessing on the quantitative determination of nutrient content in poultry manure by near infrared spectroscopy

Determining nutrients, dry matter, and pH of liquid organic manures using visual and near-infrared spectrometry

In agriculture, overfertilization with liquid organic manures (LOM) is causing environmental issues including eutrophication of non-agricultural ecosystems and nitrate pollution of groundwater. To avoid such problems, a precise and demand-oriented fertilization with LOM is needed. This can only be achieved if the nutrient composition of the LOM is known. However, traditional chemical analysis is cost- and time-intensive and furthermore dependent on a representative sample. Optical spectrometry in the visible and near-infrared range could provide an efficient alternative, if a chemometric calibration assures sufficient accuracy. To improve chemometric calibration, this study investigated several spectral preprocessing and regression algorithms, and compared predictions based either on dry or wet weight concentration. In addition, the capability of low-cost spectrometers was evaluated by simulating low-resolution spectra with smaller wavelength ranges. The reflectance spectra of 391 pig manure, 155 cattle manure, and 89 biogas digestate samples were used to predict plant macronutrients (N, P, K, Mg, Ca, S), micronutrients (Mn, Fe, Cu, Zn, B), dry matter (DM) and pH. The experiments demonstrate the general aptness of optical spectrometry to accurately predict DM, pH and all nutrients except boron in pig, cattle, and digestate LOM, even with simulated low-cost spectrometers. Best results show r2 between 0.80 and 0.97, ratios of performance to interquartile distance (RPIQ) between 2.1 and 7.8, and mean absolute errors normalized by the median (nMAE) between 5 and 36 %. The regression methods PLSR, LASSO, and least angle regression predominantly performed best. The innovative preprocessing methods named simple ratios (SR) and normalized differences (ND) proved to be very useful algorithms, especially for N and P predictions, outperforming the accuracy of classical techniques in several cases. Concentrations on dry weight basis improved predictions of K, Mn, and pH.

Open-source python module for automated preprocessing of near infrared spectroscopic data

Near infrared spectroscopy (NIRS) is an analytical technique for determining the chemical composition or structure of a given sample. For several decades, NIRS has been a frequently used analysis tool in agriculture, pharmacology, medicine, and petrochemistry. The popularity of NIRS is constantly growing as new application areas are discovered. Contrary to mid infrared spectral region, the absorption bands in near infrared spectral region are often non-specific, broad, and overlapping. Analysis of NIR spectra requires multivariate methods which are highly subjective to noise arising from instrumentation, scattering effects, and measurement setup. NIRS measurements are also frequently performed outside of a laboratory which further contributes to the presence of noise. Therefore, preprocessing is a critical step in NIRS as it can vastly improve the performance of multivariate models. While extensive research regarding various preprocessing methods exists, selection of the best preprocessing method is often determined through trial-and-error. A more powerful approach for optimizing preprocessing in NIRS models would be to automatically compare a large number of preprocessing techniques (e.g., through grid-search or hyperparameter tuning). To enable this, we present, nippy, an open-source Python module for semi-automatic comparison of NIRS preprocessing methods (available at https://github.com/uef-bbc/nippy). We provide here a brief overview of the capabilities of nippy and demonstrate the typical usage through two examples with public datasets.

Hyperspectral-based Inversion of Heavy Metal Content in the Soil of Coal Mining Areas

Coal mining has environmental impacts on surrounding areas, including heavy metal contamination of soil. This study explores the feasibility of using hyperspectral remote sensing to determine the heavy metal (Cr, Ni, Cu, Zn, Cd, Pb) content of soils in a coal-mining area in the city of Zoucheng, Shandong Province, China. We used a plasma mass spectrometer to measure the heavy metal contents of soils and an ASD Field Spec4 spectrometer to measure soil hyperspectral data. Savitzky-Golay (SG) convolution smoothing and multiplicative scatter correction (MSC) were applied to the data, along with multiple mathematical transformations. Finally, a regression model for estimating heavy metal content of soils was developed using partial least squares regression (PLSR) analysis. Results show that the average heavy metal content of study soils was lower than the national standard value of soil environmental quality. The model's predictive accuracy is extremely high for Ni ( = 0.923 and RMSE = 0.831 by modeling; = 0.879 and RMSE = 1.292 by testing); ideal for Cr, Cu, Zn, and Pb; and insufficient for Cd. Preprocessing the reflectance spectra with SG convolution smoothing in combination with MSC and reciprocal logarithm transformation yields the highest model accuracy. Hyperspectral PLSR modeling can effectively predict heavy metal content of soils in coal-mining areas, and preprocessing spectral data is crucial for achieving high prediction accuracy.

Onsite and online FT-NIR spectroscopy for the estimation of total nitrogen and moisture content in poultry manure

The nitrogen and moisture of manure are highly variable parameters and depend on animal type, husbandry techniques, environmental conditions and storage time. The precision in manure dose estimation for crops fertilization depends on the total nitrogen and moisture content just before its incorporation in the field. The aim of the study is to develop a Fourier Transform Near Infrared (FT-NIR) spectroscopy method to determine the total Kjeldhal nitrogen (TKN%) and moisture (M%) of different types of poultry manure prior to land application. Samples covering a wide range of poultry types and different husbandry conditions were obtained from farms of North-Eastern Italy in order to develop the method. The method was calibrated (R(2) = 0.94 for TKN%, R(2) = 0.99 for M%) and validated (R(2) = 0.82 for TKN%, R(2) = 0.95 for M%) in the laboratory. An external validation was also performed in situ with independent samples, of similar origin to the previous data set, which were collected just before application in the field. Spectra acquisitions for these samples were carried out using the same instrumentation which was placed in a special vehicle for monitoring campaigns. The results showed satisfactory prediction accuracy (R(2) = 0.82 for TKN%, R(2) = 0.93 for M%). Finally, an additional analysis was performed to discriminate the different types of poultry effluents. The TKN and M measurements in the disposal areas indicated that current agronomic practices lead to more than double poultry manure oversupply. The proposed FT-NIR methodology aims to improve the current fertilization management and environmental protection by providing fast and precise estimations of poultry manure doses prior to land application.

Review of the application of near-infrared spectroscopy technology to determine the chemical composition of animal manure

Animal manure contains a variety of chemical constituents that are highly valuable to agriculture, including nitrogen, phosphorus, potassium, and metal micronutrients. Although appropriately applied manure has numerous positive attributes, the excessive application of manure may lead to pollution of the atmosphere, water, or soil. To reconcile precision agriculture and the potential negative environmental influences of animal manure, it is necessary to develop rapid and robust methods to evaluate the chemical composition of animal manure. This paper summarizes recent advances in near-infrared reflectance spectroscopy (NIRS) in predicting moisture, dry matter, organic matter, nitrogen, phosphorus, carbon, and metal content in animal manure. The results indicate the high potential of NIRS as an efficient tool for monitoring the chemical composition of animal manure. Future prospects and needs related to increasing the feasibility of the industrial application of NIRS and improving NIRS prediction precision in determining the chemical composition of animal manure are discussed.