Explore the vast range of titles available.

Sugarcane is one of the leading commercial crops grown in India. The prevailing weather during the various crop-growth stages significantly impacts sugarcane productivity and the quality of its juice. The objective of this study was to predict the yield of sugarcane during different growth periods using machine learning techniques viz., random forest (RF), support vector machine (SVM), stepwise multiple linear regression (SMLR) and artificial neural networks (ANN). The performance of different yield forecasting models was assessed based on the coefficient of determination (R2), root mean square error (RMSE), normalized root mean square error (nRMSE) and model efficiency (EF). Among the models, ANN model was able to predict the yield at different growth stages with higher R2 and lower nRMSE during both calibration and validation. The performance of models across the forecasts was ranked based on the model efficiency as ANN > RF > SVM > SMLR. This study demonstrated that the ANN model can be used for reliable yield forecasting of sugarcane at different growth stages.

Early information exchange regarding predicted crop production could play a role in lowering the danger of food insecurity. In this study total six multivariate models were developed using past time series yield data and weather indices viz. SMLR, PCA-SMLR, ANN, PCA-ANN, SMLR-ANN and PCA-SMLR-ANN for three major soybean producing districts of Uttarakhand viz. Almora, Udham Singh Nagar and Uttarkashi. Further analysis was done by fixing 80% of the data for calibration and the remaining dataset for validation to predict soybean yield. Phenology wise average values were computed using the daily weather data. These average values are subsequently employed in the computation of both weighted and unweighted weather indices. The PCA-SMLR-ANN, SMLR-ANN and PCA-ANN models were found to be the best soybean yield predictor model for Almora, Udham Singh Nagar and Uttarkashi districts, respectively. The overall ranking based on the performances of the models for all locations can be given as: SMLR-ANN > PCA-ANN > PCA-SMLR-ANN ≈ ANN > PCA-SMLR > SMLR. The study results indicated that hybrid models outperformed the individual models well for all the study regions.

Multi-spectral remote sensing of green vegetation provides an opportunity for assessing biophysical and biochemical properties. This technique could play a crucial role in pasture management by providing the means to evaluate pasture quality in situ. In this study, the potential of a 16-channel multi-spectral radiometer (MSR) for predicting pasture quality, crude protein (CP), acid detergent fibre (ADF), neutral detergent fibre (NDF), ash, dietary cation–anion difference (DCAD), lignin, lipid, metabolisable energy (ME) and organic matter digestibility (OMD) was evaluated. In situ canopy spectral reflectance was acquired from mixed pastures, under commercial farm conditions in New Zealand. The multi-spectral data were evaluated by single wavelength, linear and non-linear renormalized difference vegetation index (RDVI), and stepwise multiple linear regression (SMLR) models. The selected non-linear, exponential fit, RDVI index models described (0.65 ≤ r 2 ≤ 0.85) of the variation of pasture quality components (CP, DCAD, ME and OMD), while CP, ash, DCAD, lipid, ME and OMD were estimated with moderate accuracy (0.60 ≤ r 2 ≤ 0.80) by the SMLR model. The remaining pasture quality components ADF, NDF and lignin were poorly explained (0.40 ≤ r 2 ≤ 0.58) by the models. This experiment concluded that the MSR has potential to rapidly estimate pasture quality in the field using non-destructive sampling.

Productivity and botanical composition of legume-grass swards in rotation systems are important factors for successful arable farming in both organic and conventional farming systems. As these attributes vary considerably within a field, a non-destructive method of detection while doing other tasks would facilitate more targeted management of crops and nutrients in the soil–plant–animal system. Two pot experiments were conducted to examine the potential of field spectroscopy to assess total biomass and the proportions of legume, using binary mixtures and pure swards of grass and legumes. The spectral reflectance of swards was measured under artificial light conditions at a sward age ranging from 21 to 70 days. Total biomass was determined by modified partial least squares (MPLS) regression, stepwise multiple linear regression (SMLR) and the vegetation indices (VIs) simple ratio (SR), normalized difference vegetation index (NDVI), enhanced vegetation index (EVI) and red edge position (REP). Modified partial least squares and SMLR gave the largest R 2 values ranging from 0.85 to 0.99. Total biomass prediction by VIs resulted in R 2 values of 0.87–0.90 for swards with large leaf to stem ratios; the greatest accuracy was for EVI. For more mature and open swards VI-based detection of biomass was not possible. The contribution of legumes to the sward could be determined at a constant biomass level by the VIs, but this was not possible when the level of biomass varied.

Quantitative structure–activity relationship (QSAR) is a mathematical function that can be used to estimate biological activities of compounds based on their chemical structures. Molecular descriptors, the form of numerical descriptions that capture the structural characteristics, are used for QSAR. Mold 2 descriptors are calculated from two‐dimensional structures. They are freely available to the public (http://www.fda.gov/ScienceResearch/BioinformaticsTools/Mold2/default.htm). In this chapter, we will give a brief description of Mold 2 descriptors, and comparison of Mold 2 descriptors with molecular descriptors from other software packages. We will also demonstrate applications of Mold 2 descriptors in both qualitative and quantitative QSAR modeling.

Rangelands provide significant environmental benefits through many ecosystem services, which may include soil organic carbon (SOC) sequestration. However, quantifying SOC stocks and monitoring carbon (C) fluxes in rangelands are challenging due to the considerable spatial and temporal variability tied to rangeland C dynamics as well as limited data availability. We developed the Rangeland Carbon Tracking and Management (RCTM) system to track long‐term changes in SOC and ecosystem C fluxes by leveraging remote sensing inputs and environmental variable data sets with algorithms representing terrestrial C‐cycle processes. Bayesian calibration was conducted using quality‐controlled C flux data sets obtained from 61 Ameriflux and NEON flux tower sites from Western and Midwestern US rangelands to parameterize the model according to dominant vegetation classes (perennial and/or annual grass, grass‐shrub mixture, and grass‐tree mixture). The resulting RCTM system produced higher model accuracy for estimating annual cumulative gross primary productivity (GPP) (R2 > 0.6, RMSE <390 g C m−2) relative to net ecosystem exchange of CO2 (NEE) (R2 > 0.4, RMSE <180 g C m−2). Model performance in estimating rangeland C fluxes varied by season and vegetation type. The RCTM captured the spatial variability of SOC stocks with R2 = 0.6 when validated against SOC measurements across 13 NEON sites. Model simulations indicated slightly enhanced SOC stocks for the flux tower sites during the past decade, which is mainly driven by an increase in precipitation. Future efforts to refine the RCTM system will benefit from long‐term network‐based monitoring of vegetation biomass, C fluxes, and SOC stocks. Plain Language Summary Rangelands play a crucial role in providing various ecosystem services, including potential climate change mitigation through increased soil organic carbon (SOC) storage. Accurate estimates of changes in carbon (C) storage are challenging due to the heterogeneous nature of rangelands and the limited availability of field observations. In this work, we leveraged remote sensing observations, tower‐based C flux measurements from over 60 rangeland sites in the Western and Midwestern US, and other environmental data sets to build the process‐based Rangeland Carbon Tracking and Management (RCTM) modeling system. The RCTM system is designed to simulate the past 20 years of rangeland C dynamics and is regionally calibrated. The RCTM system performs well in estimating spatial and temporal rangeland C fluxes as well as spatial SOC storage. Model simulation results revealed increased SOC storage and rangeland productivity driven by annual precipitation patterns. The RCTM system developed by this work can be used to generate accurate spatial and temporal estimates of SOC storage and C fluxes at fine spatial (30 m) and temporal (every 5 days) resolutions, and is well‐suited for informing rangeland C management strategies and improving broad‐scale policy making. Key Points The Rangeland Carbon Tracking and Monitoring System was calibrated to simulate vegetation type‐specific rangeland C dynamics Regional variability in carbon fluxes and soil organic carbon is well represented by a remote sensing‐driven process modeling approach Soil organic carbon stocks in Western and Midwestern US rangelands increased over the past 20 years due to increased precipitation