Machine Learning Regression Algorithms Research Articles

Assessment of maize nitrogen uptake from PRISMA hyperspectral data through hybrid modelling

ABSTRACT The spaceborne imaging spectroscopy mission PRecursore IperSpettrale della Missione Applicativa (PRISMA), launched on 22 March 2019 by the Italian Space Agency, opens new opportunities in many scientific domains, including precision farming and sustainable agriculture. This new Earth Observation (EO) data stream requires new-generation approaches for the estimation of important biophysical crop variables (BVs). In this framework, this study evaluated a hybrid approach, combining the radiative transfer model PROSAIL-PRO and several machine learning (ML) regression algorithms, for the retrieval of canopy chlorophyll content (CCC) and canopy nitrogen content (CNC) from synthetic PRISMA data. PRISMA-like data were simulated from two images acquired by the airborne sensor HyPlant, during a campaign performed in Grosseto (Italy) in 2018. CCC and CNC estimations, assessed from the best performing ML algorithms, were used to define two relations with plant nitrogen uptake (PNU). CNC proved to be slightly more correlated to PNU than CCC (R 2 = 0.82 and R 2 = 0.80, respectively). The CNC-PNU model was then applied to actual PRISMA images acquired in 2020. The results showed that the estimated PNU values are within the expected ranges, and the temporal trends are compatible with plant phenology stages.

Activated recovery of PVC from contaminated waste extension cord-cable using a weak acid.

Waste electronic and electrical equipment are complex mixtures of valuable and/or toxic materials, which pose serious challenges in their recycling or disposal, for example, electrical transmission wires insulated in polyvinyl chloride materials. These materials are frequently found contaminated with toxic chemical elements, such as Pb, Hg, Cr, or Cd, and are discarded without decontamination. To resolve this problem, we developed a microwave-assisted extraction process to remove toxic metals from plastic e-waste. We processed diluted (30wt%) citric acid at 210°C for 1h inside a pressurized vessel heated by microwave, and found it was suitable not only for the extraction of the toxic metals (∼100%) but also for a significant plastic recovery (>50wt%). To predict an optimized process window, the support vector regression machine learning algorithm was applied, which reduced the amount of experimentation required while still giving accurate results. Conditions optimized for the reference sample also led to maximum extraction of toxic metals from real-life extension cord waste. We also report that the recovered plastic's properties remained intact after the extraction.

Comparison of Models to Predict Mechanical Properties of FR-AM Composites and a Fractographical Study

Continuous fiber-reinforced additive manufacturing (cFRAM) composites improve the mechanical properties of polymer components. Given the recent interest in their mechanical performance and failure mechanisms, this work aims to describe the principal failure mechanisms and compare the prediction capabilities for the mechanical properties, stiffness constants, and strength of cFRAM using two distinct predictive models. This work presents experimental tensile tests of continuous carbon fiber AM composites varying their reinforced fraction, printing direction, and fiber angle. In the first predictive model, a micromechanical-based model for stiffness and strength predicts their macroscopic response. In the second part, data-driven models using different machine learning algorithms for regression are trained to predict stiffness and strength based on critical parameters. Both models are assessed regarding their accuracy, ease of implementation, and generalization capabilities. Moreover, microstructural images are used for a qualitative evaluation of the parameters and their influence on the macroscopic response and failure surface topology. Finally, we conclude that although predicting the mechanical properties of cFRAM is a complex task, it can be carried on a Gaussian process regression and a micromechanical model, with good accuracy generalized onto different process parameters specimens.

Gap Filling Cloudy Sentinel-2 NDVI and NDWI Pixels with Multi-Frequency Denoised C-Band and L-Band Synthetic Aperture Radar (SAR), Texture, and Shallow Learning Techniques

Multispectral imagery provides unprecedented information on Earth system processes: however, data gaps due to clouds and shadows are a major limitation. Normalized-Difference Vegetation Index (NDVI) and Normalized-Difference Water Index (NDWI) are two spectral indexes employed for monitoring vegetation phenology, land-cover change and more. Synthetic Aperture Radar (SAR) with its cloud-penetrating abilities can fill data gaps using coincident imagery. In this study, we evaluated C-band Sentinel-1, L-band Uninhabited Aerial Vehicle SAR (UAVSAR) and texture for gap filling using efficient machine learning regression algorithms across three seasons. Multiple models were evaluated including Support Vector Machine, Random Forest, Gradient Boosted Trees and an ensemble of models. The Gap filling ability of SAR was evaluated with Sentinel-2 imagery from the same date, 3 days and 8 days later than both SAR sensors in September. Sentinel-1 and Sentinel-2 imagery from winter and spring seasons were also evaluated. Because SAR imagery contains noise, we compared two robust de-noising methods and evaluated performance against a refined lee speckle filter. Mean Absolute Error (MAE) rates of the cloud gap-filling model were assessed across different dataset combinations and land covers. The results indicated de-noised Sentinel-1 SAR and UAVSAR with GLCM texture provided the highest predictive abilities with random forest R2 = 0.91 (±0.014), MAE = 0.078 (±0.003) (NDWI) and R2 = 0.868 (±0.015), MAE = 0.094 (±0.003) (NDVI) during September. The highest errors were observed across bare ground and forest, while the lowest errors were on herbaceous and woody wetland. Results on January and June imagery without UAVSAR were less strong at R2 = 0.60 (±0.036), MAE = 0.211 (±0.005) (NDVI), R2 = 0.61 (±0.043), MAE = 0.209 (±0.005) (NDWI) for January and R2 = 0.72 (±0.018), MAE = 0.142 (±0.004) (NDVI), R2 = 0.77 (±0.022), MAE = 0.125 (±0.004) (NDWI) for June. Ultimately, the results suggest de-noised C-band SAR with texture metrics can accurately predict NDVI and NDWI for gap-filling clouds during most seasons. These shallow machine learning models are rapidly trained and applied faster than intensive deep learning or time series methods.

Modeling the Leaf Area Index of Inner Mongolia Grassland Based on Machine Learning Regression Algorithms Incorporating Empirical Knowledge

Leaf area index (LAI) is one of the key biophysical indicators for characterizing the growth and status of vegetation and is also used in modeling earth system processes. Machine learning algorithms (MLAs) such as random forest regression (RFR), artificial neural network regression (ANNR) and support vector regression (SVR) based on satellite data have been widely used for the estimation of LAI. However, the selection of input variables has a great impact on the estimation performance of MLAs. In this study, we aimed to improve the LAI inversion model of Inner Mongolia grassland based on MLAs incorporating empirical knowledge. Firstly, we used the ANNR, SVR and RFR approaches, respectively, to rank the input variables including vegetation indices, climate factors, soil factors and topography factors and found that Normalized Difference Phenology Index (NDPI) contributed the most to LAI estimation. Secondly, we selected four sets of input variables, namely, all variables—A, model selected variables—B, overlapping variables—C and self-defined variables—D, respectively. Subsequently, we built twelve LAI estimation models (RFR-A, RFR-B, RFR-C, etc.) based on three MLAs and four sets of input variables. The evaluation of them showed the RFR produced higher prediction accuracy, followed by ANNR and SVR. Furthermore, the RFR-D presented the highest accuracy in predicting LAI (R2 = 0.55, RMSE = 0.37 m2/m2, MAE = 0.29 m2/m2). Finally, we compared our results with MODIS LAI and GEOV2 LAI products and found that all of them showed a similar spatial distribution of grassland LAI in the four sub-regions covering all grassland types, but our model exhibited larger LAI values in the desert steppe and smaller LAI values in the others. These findings demonstrated that MLAs incorporating empirical knowledge could improve the accuracy of modelling LAI and further study is necessary to reduce the uncertainty in LAI mapping in grassland.

Estimation of chlorophyll, macronutrients and water content in maize from hyperspectral data using machine learning and explainable artificial intelligence techniques

ABSTRACT We used the secondary hyperspectral data set (leaf reflectance of maize) taken in the spectral range from 350 to 2500 nm in a field (under low and high nitrogen conditions) and glasshouse experiment. Water, chlorophyll, nitrogen (N), phosphorus (P) and potassium (K) contents of maize leaves taken from these experiments were measured using the standard methods. Six machine learning regression algorithms (Random Forest, Support Vector Regression, k-Nearest Neighbours, Multilayer Perceptron, Gradient Boosting Regression and Partial Least Square Regression) were used for development of the models to predict these parameters from leaf reflectance data. Each plant parameter was estimated with a different machine learning algorithm. Explainable artificial intelligence methods were used to identify the optimum wavelengths for each parameter. The wavelengths in the short-wave infrared (SWIR) region were found optimum for estimating the water content across the three N regimes, and the red-edge band for chlorophyll. The optimum wavelengths for estimating N content in leaves were in the green spectral region under low N status, near-infrared (NIR) and SWIR regions under greenhouse and SWIR region under high N status. The important wavelengths for estimating P in maize leaves were 1088, 1262 and 1263 nm under low N status and the SWIR range under high N status and greenhouse conditions. The SWIR band was useful for estimating the K content in leaves.

Model-free prediction test with application to genomics data

Testing the significance of predictors in a regression model is one of the most important topics in statistics. This problem is especially difficult without any parametric assumptions on the data. This paper aims to test the null hypothesis that given confounding variables Z, X does not significantly contribute to the prediction of Y under the model-free setting, where X and Z are possibly high dimensional. We propose a general framework that first fits nonparametric machine learning regression algorithms on [Formula: see text] and [Formula: see text], then compares the prediction power of the two models. The proposed method allows us to leverage the strength of the most powerful regression algorithms developed in the modern machine learning community. The P value for the test can be easily obtained by permutation. In simulations, we find that the proposed method is more powerful compared to existing methods. The proposed method allows us to draw biologically meaningful conclusions from two gene expression data analyses without strong distributional assumptions: 1) testing the prediction power of sequencing RNA for the proteins in cellular indexing of transcriptomes and epitopes by sequencing data and 2) identification of spatially variable genes in spatially resolved transcriptomics data.

Exploring Transferable Techniques to Retrieve Crop Biophysical and Biochemical Variables Using Sentinel-2 Data

The current study aimed to determine the spatial transferability of eXtreme Gradient Boosting (XGBoost) models for estimating biophysical and biochemical variables (BVs), using Sentinel-2 data. The specific objectives were to: (1) assess the effect of different proportions of training samples (i.e., 25%, 50%, and 75%) available at the Target site (DT) on the spatial transferability of the XGBoost models and (2) evaluate the effect of the Source site (DS) (i.e., trained) model accuracy on the Target site (i.e., unseen) retrieval uncertainty. The results showed that the Bothaville (DS) → Harrismith (DT) Leaf Area Index (LAI) models required only fewer proportions, i.e., 25% or 50%, of the training samples to make optimal retrievals in the DT (i.e., RMSE: 0.61 m2 m−2; R2: 59%), while Harrismith (DS) →Bothaville (DT) LAI models required up to 75% of training samples in the DT to obtain optimal LAI retrievals (i.e., RMSE = 0.63 m2 m−2; R2 = 67%). In contrast, the chlorophyll content models for Bothaville (DS) → Harrismith (DT) required significant proportions of samples (i.e., 75%) from the DT to make optimal retrievals of Leaf Chlorophyll Content (LCab) (i.e., RMSE: 7.09 µg cm−2; R2: 58%) and Canopy Chlorophyll Content (CCC) (i.e., RMSE: 36.3 µg cm−2; R2: 61%), while Harrismith (DS) →Bothaville (DT) models required only 25% of the samples to achieve RMSEs of 8.16 µg cm−2 (R2: 83%) and 40.25 µg cm−2 (R2: 77%), for LCab and CCC, respectively. The results also showed that the source site model accuracy led to better transferability for LAI retrievals. In contrast, the accuracy of LCab and CCC source site models did not necessarily improve their transferability. Overall, the results elucidate the potential of transferable Machine Learning Regression Algorithms and are significant for the rapid retrieval of important crop BVs in data-scarce areas, thus facilitating spatially-explicit information for site-specific farm management.

Improving the pulsed neutron-gamma density method with machine learning regression algorithms

Formation bulk density is one of the critical parameters for formation evaluation. As a safe and environmentally friendly method, the pulsed neutron-gamma density (NGD) measurement is emerging as an alternative to the traditional chemical source-based gamma-gamma density (GGD) measurement. However, in the NGD measurement, the initial energy spectrum, source intensity, and spatial distribution of the secondary inelastic gamma-ray source vary with formation components. Moreover, the energy of inelastic gamma rays is at the MeV level, leading to a non-negligible pair production effect. All these factors affect the accuracy of the bulk-density measurement. In addition, the impact of borehole configuration on NGD is evident, and correction for borehole effects is essential. To improve density accuracy: first, we forgo exploring an explicit theoretical formula for density calculation and instead treat the NGD mathematically as a regression problem and introduce the machine learning regressor, a powerful and popular tool for solving regression problems, into the NGD for the first time; second, we select features less affected by changes in formation chemical composition as input features. Our results show that the final three tuned machine learning regressors selected from the 39 candidate regressors outperform the optimized polynomial model (an optimization of conventional density calculation models) in both accuracy and generalization ability. They complete density prediction and borehole correction in one step, avoiding complex exploration of borehole effects as in the optimized polynomial model and dramatically simplifying the borehole correction process. Moreover, the GaussianProcessRegressor can complete borehole correction without the standoff information and perform well, which is impossible for the optimized polynomial model, broadening application scenarios.

Correcting for filter-based aerosol light absorption biases at the Atmospheric Radiation Measurement program's Southern Great Plains site using photoacoustic measurements and machine learning

Abstract. Measurement of light absorption of solar radiation by aerosols is vital for assessing direct aerosol radiative forcing, which affects local and global climate. Low-cost and easy-to-operate filter-based instruments, such as the Particle Soot Absorption Photometer (PSAP), that collect aerosols on a filter and measure light attenuation through the filter are widely used to infer aerosol light absorption. However, filter-based absorption measurements are subject to artifacts that are difficult to quantify. These artifacts are associated with the presence of the filter medium and the complex interactions between the filter fibers and accumulated aerosols. Various correction algorithms have been introduced to correct for the filter-based absorption coefficient measurements toward predicting the particle-phase absorption coefficient (Babs). However, the inability of these algorithms to incorporate into their formulations the complex matrix of influencing parameters such as particle asymmetry parameter, particle size, and particle penetration depth results in prediction of particle-phase absorption coefficients with relatively low accuracy. The analytical forms of corrections also suffer from a lack of universal applicability: different corrections are required for rural and urban sites across the world. In this study, we analyzed and compared 3 months of high-time-resolution ambient aerosol absorption data collected synchronously using a three-wavelength photoacoustic absorption spectrometer (PASS) and PSAP. Both instruments were operated on the same sampling inlet at the Department of Energy's Atmospheric Radiation Measurement program's Southern Great Plains (SGP) user facility in Oklahoma. We implemented the two most commonly used analytical correction algorithms, namely, Virkkula (2010) and the average of Virkkula (2010) and Ogren (2010)–Bond et al. (1999) as well as a random forest regression (RFR) machine learning algorithm to predict Babs values from the PSAP's filter-based measurements. The predicted Babs was compared against the reference Babs measured by the PASS. The RFR algorithm performed the best by yielding the lowest root mean square error of prediction. The algorithm was trained using input datasets from the PSAP (transmission and uncorrected absorption coefficient), a co-located nephelometer (scattering coefficients), and the Aerosol Chemical Speciation Monitor (mass concentration of non-refractory aerosol particles). A revised form of the Virkkula (2010) algorithm suitable for the SGP site has been proposed; however, its performance yields approximately 2-fold errors when compared to the RFR algorithm. To generalize the accuracy and applicability of our proposed RFR algorithm, we trained and tested it on a dataset of laboratory measurements of combustion aerosols. Input variables to the algorithm included the aerosol number size distribution from the Scanning Mobility Particle Sizer, absorption coefficients from the filter-based Tricolor Absorption Photometer, and scattering coefficients from a multiwavelength nephelometer. The RFR algorithm predicted Babs values within 5 % of the reference Babs measured by the multiwavelength PASS during the laboratory experiments. Thus, we show that machine learning approaches offer a promising path to correct for biases in long-term filter-based absorption datasets and accurately quantify their variability and trends needed for robust radiative forcing determination.

Stemness inhibition by (+)-JQ1 in canine and human mammary cancer cells revealed by machine learning

Stemness is a phenotype associated with cancer initiation and progression, malignancy, and therapeutic resistance, exhibiting particular molecular signatures. Targeting stemness has been proposed as a promising strategy against breast cancer stem cells that can play a key role in breast cancer progression, metastasis, and multiple drug resistance. Here, using a previously published one-class logistic regression machine learning algorithm (OCLR) built on pluripotent stem cells to predict stemness in human cancer samples, we provide the stemness index (mRNAsi) of different canine non-tumor and mammary cancer cells. Then, we confirmed that inhibition of BET proteins by (+)-JQ1 reduces stemness in a high mRNAsi canine cancer cell. Furthermore, using public data, we observed that (+)-JQ1 can also decrease stemness in human triple-negative breast cancer cells. Our work suggests that mRNAsi can be used to estimate stemness in different species and confirm epigenetic modulation by BET inhibition as a promising strategy for modulating the stemness phenotype in canine and human mammary cancer cells.

Inversion of the hybrid machine learning model to estimate leaf area index of winter wheat from GaoFen-6 WFV imagery

The leaf area index (LAI) is an important agroecological physiological parameter affecting vegetation growth and is an essential indicator for estimating crop growth. To apply the hybrid machine learning model to the remote sensing inversion of winter wheat LAI at three growth stages based on the wide field of view (WFV) of the GaoFen-6 (GF-6 WFV) images, the Xiangfu District in the east of Kaifeng City, Henan Province, was selected as the testing region. The LAI values, which were simulated using the CERES-wheat model, were an input for the PROSAIL model to simulate spectral reflectance. Different machine learning regression algorithms (MLRA) were trained with simulated spectra reflectance by PROSAIL and subsequently applied to the GF-6 WFV reflectance spectra. The random forest regression (RFR) model achieved reliable LAI estimates at the three growth stages. CERES-wheat and PROSAIL preserved the most informative spectra reflectance for LAI estimation so that each RFR could achieve satisfactory estimation results. The hybrid machine learning model could accurately reverse the growth state of winter wheat in three growth stages.

UAV-based multispectral and thermal cameras to predict soil water content – A machine learning approach

Soil water content (SWC) estimation is a crucial issue of agricultural production, and its mapping is an important task. We aimed to study the efficacy of UAV-based thermal (TH) and multispectral (MS) cameras in SWC mapping. Soil samples were collected and the SWC content was determined in a laboratory as reference data and four machine learning regression algorithms (Random Forest [RF], Elastic Net [ENR], General Linear Model [GLM], Robust Linear Model [RLM]) were tested for the prediction efficacy, combined with three pixel value extraction methods (single pixel, mean of 20 and 30 cm radius buffer). We found that MS cameras ensured better input data than TH cameras: R2s were 0.97 vs 0.71, mean-normalized root mean square errors (nRMSE) were 10 vs 25 %, respectively. Best models were obtained by the RF (0.97 R2) and ENR (0.88 R2) in case of MS camera. Relationship between SWC and thermal data was exponential, which was incorrectly handled by the GLM (>40 % nRMSE; furthermore, RLM and ENR was not working with only one variable), thus, TH data was acceptable only with the RF (24.4 % nRMSE). Single pixel extraction provided the best input for the estimations, mean of buffered areas did not perform better in the models. Maps provided appropriate SWC estimations according to the nRMSEs, with high spatial resolution. In spite of potential inaccuracies, visualizing the spatial heterogeneities can be a great help to farmers to increase the efficacy of planning irrigation in precision agriculture.

Machine learning models predict total charges and drivers of cost for transcatheter aortic valve replacement

BackgroundGiven the increasing healthcare costs, there is an interest in developing machine learning (ML) prediction models for estimating hospitalization charges. We use ML algorithms to predict hospitalization charges for patients undergoing transfemoral transcatheter aortic valve replacement (TF-TAVR) utilizing the National Inpatient Sample (NIS) database.MethodsPatients who underwent TF-TAVR from 2012 to 2016 were included in the study. The primary outcome was total hospitalization charges. Study dataset was divided into 80% training and 20% testing sets. We used following ML regression algorithms: random forest, gradient boosting, k-nearest neighbors (KNN), multi-layer perceptron and linear regression. ML algorithms were built for for 3 stages: Stage 1, including variables that were known pre-procedurally (prior to TF-TAVR); Stage 2, including variables that were known post-procedurally; Stage 3, including length of stay (LOS) in addition to the stage 2 variables.ResultsA total of 18,793 hospitalization for TF-TAVR were analyzed. The mean and median adjusted hospitalization charges were $220,725.2 ($137,675.1) and $187,212.0 ($137,971.0–264,824.8) respectively. Random forest regression algorithm outperformed other ML algorithms at all stages with higher R2 score and lower mean absolute error (MAE), root mean squared area (RMSE) and root mean squared logarithmic error (RMSLE) (Stage 1: MAE 79,979.11, R2 0.157; Stage 2: MAE 76,200.09, R2 0.256; Stage 3: MAE 69,350.09, R2 0.453). LOS was the most important predictor of hospitalization charges.ConclusionsWe built ML algorithms that predict hospitalization charges with good accuracy in patients undergoing TF-TAVR at different stages of hospitalization and that can be used by healthcare providers to better understand the drivers of charges.

Machine-learning-based prediction of hydrogen adsorption capacity at varied temperatures and pressures for MOFs adsorbents

BackgroundMetal-organic frameworks (MOFs) have been recently studied as promising hydrogen storage adsorbents. However, large-scale screening by experiments is infeasible. Machine learning and Grand Canonical Monte Carlo (GCMC) have been widely applied in the screening of MOFs to greatly improve efficiency. MethodsGCMC was applied to 418 MOFs to calculate structural and performance parameters, and the gradient boosted regression (GBR) machine learning algorithm was used to predict the hydrogen adsorption capacity at cryogenic temperatures and high pressures from room temperatures and low pressures, and the database was extended to 8024 MOFs adsorbents based on the established ML model. The influencing factors affecting hydrogen adsorption capacity were comprehensively evaluated, and four representative MOFs were randomly selected for hydrogen adsorption isotherm testing, and the accuracy of ML was verified by comparing the GCMC simulation results with those predicted by ML. Significant findingsThe accuracy of the ML model is acceptable, with the coefficient of determination (R2) of the train all exceeding 0.9 and the test R2 all exceeding 0.85. The MOFs exhibiting high hydrogen adsorption capacity by low-pressure adsorption have low pore size, Henry's constants, and density, and the metal-based is Al-based and Zn-based, while the surface area dominates at high-pressure adsorption. The experimentally tested MOFs with hydrogen adsorption capacity compared with GCMC simulation and ML models have an error of 1.01% in the low-pressure region and 1.49% in the high-pressure region.

Convolutional neural networks for mapping of lake sediment core particle size using hyperspectral imaging

The particle size of lake sediments integrates important environmental information, and the detection of changes in this variable over time provides important information for understanding ecosystem and sedimentary processes. Although standard machine learning regression algorithms especially random forest (RF) have shown great potential for particle size mapping in sediment cores using hyperspectral imaging, no research has yet applied deep learning approaches. One-dimensional convolutional neural networks (CNN) have recently been developed and applied in several applications in the field of spectroscopy. This study addresses this issue by developing and applying a new methodology based on a 1D convolutional autoencoder as the feature extractor and a 1D CNN architecture for regression. The proposed architecture was applied to hyperspectral images of nine lake sediment cores across Canada and evaluated against results of the RF algorithm. However, in order for the results to be comparable, the RF algorithm was performed on features that also resulted from the convolutional autoencoder. According to the leave-one-out evaluation method, the proposed CNN method represented an improvement of 14%, 4.58, 5.45, and 0.83 for R2, MAE, RMSE, and RPD, respectively, relative to the best RF algorithm. Our findings show that the proposed method can be reliably used to reconstruct particle size in sediment cores from lakes of varying climatic and environmental characteristics.

Prediction of Gross Calorific Value of Coal using Machine Learning Algorithm

Abstract: The rising number of occurrences of coal grade slippage among coal suppliers and users is causing worry in the Indian coal industry.One of the most important metrics for determining coal quality is the Gross Calorific Value (GCV). As a result, good GCV prediction is one of the essential techniques to boost heating value and coal output. This system aims to estimate the GCV of the coal samples from proximate and ultimate parameters of coal using machine learning regression algorithm: the Multiple Linear Regression (MLR) and Local Polynomial Regression (LPR). The performance of this system is evaluated using Coefficient of determination (R2 ), Root Mean Squared Error (RMSE), and Mean Absolute Error (MAE) parameters. The results of the proposed system in terms of RMSE, MAE, and R2 of the MLR and LPR are observed as 0.124, 0.119, 0.414, and 0.654, 0.547, and 0.414, respectively.

Twitter Sentiment Analysis Using NLTK and Machine Learning

Abstract: In today’s online social networks like twitter all people choose to express their opinions on social networking sites about the products or organizations, if any of the user has a good experience with any of the product or company, he/she will express their views which can be good reviews/opinion by seeing these opinion other users can know the quality of the product. On Internet, opinion mining which can be on sentiments or topic helps users to know the quality of any of the organizations or products, while developing new techniques to detect the sentiments from these opinions, all existing techniques that are used to discover are either Positive or Negative or Neutral sentiments from topics but this paper proposes 5 levels of sentiments detection such as High Positive, Moderate Positive, Neutral, High Negative and Moderate Negative. To detect sentiments, we are using four Ordinal Regression machine learning algorithms such as SoftMax, Decision Tree, Random Forest and also Support Vector Regression. For classification of tweets, we used NLTK, which cleans the tweets by removing special symbols, removing stop words, word stemming, etc. In this paper the authors have discussed how these algorithms are implemented on tweets and detect the sentiments

Comparison of phycocyanin concentrations in Chaohu Lake, China, retrieved using MODIS and OLCI images

Phycocyanin (PC) concentration is used as an indicator to characterize cyanobacteria biomass while monitoring eutrophication in inland water. Remote sensing provides useful methods for quantifying PC concentration; however, there is a shortage of datasets for the long-term monitoring of PC concentration when only a single remote sensing data is used. Therefore, PC concentrations obtained from multisource remote sensing images should be compared before integrating them for long-term monitoring. In this study, machine learning (ML) regression algorithms are used to develop PC concentration retrieval models suitable for Moderate Resolution Imaging Spectroradiometer (MODIS) and Sentinel-3 Ocean and Land Colour Instrument (OLCI) images, and their accuracies are compared. The two optimal retrieval models are applied to satellite images acquired on the same days to compare the spatial consistency of the two PC concentration retrieval results. The results show that the sensitive spectral range of PC concentration is 560–680 nm. Among the ML regression algorithms, gradient boosted tree (GBT) regression exhibits the highest PC retrieval accuracy for both the MODIS images (R2 = 0.82, RMSE = 61.9 μg/L) and OLCI images (R2 = 0.86, RMSE = 45.44 μg/L). The PC concentrations retrieved from the MODIS and OLCI images acquired in bloom and no-bloom periods have a high spatial consistency in most areas of Chaohu Lake. Their correlation coefficient also exceeds 0.7, and the average relative error reaches 0.293 μg/L. However, a large difference exists in areas with high PC concentrations, which may cause by the poor applicability of atmospheric correction algorithms and PC retrieval models in these areas. The proposed PC concentration retrieval models developed using GBT regression in this paper can expend the idea for the quantitative retrieval of other inland water quality parameters in inland water, and the conclusions should enable the effective integration of MODIS and OLCI images for the time series monitoring of PC concentrations in reservoirs and lakes.

A Hybrid Approach to Tea Crop Yield Prediction Using Simulation Models and Machine Learning.

Tea (Camellia sinensis L.) is one of the most highly consumed beverages globally after water. Several countries import large quantities of tea from other countries to meet domestic needs. Therefore, accurate and timely prediction of tea yield is critical. The previous studies used statistical, deep learning, and machine learning techniques for tea yield prediction, but crop simulation models have not yet been used. However, the calibration of a simulation model for tea yield prediction and the comparison of these approaches is needed regarding the different data types. This research study aims to provide a comparative study of the methods for tea yield prediction using the Food and Agriculture Organization (FAO) of the United Nations AquaCrop simulation model and machine learning techniques. We employed weather, soil, crop, and agro-management data from 2016 to 2019 acquired from tea fields of the National Tea and High-Value Crop Research Institute (NTHRI), Pakistan, to calibrate the AquaCrop simulation model and to train regression algorithms. We achieved a mean absolute error (MAE) of 0.45 t/ha, a mean squared error (MSE) of 0.23 t/ha, and a root mean square error (RMSE) of 0.48 t/ha in the calibration of the AquaCrop model and, out of the ten regression models, we achieved the lowest MAE of 0.093 t/ha, MSE of 0.015 t/ha, and RMSE of 0.120 t/ha using 10-fold cross-validation and MAE of 0.123 t/ha, MSE of 0.024 t/ha, and RMSE of 0.154 t/ha using the XGBoost regressor with train test split. We concluded that the machine learning regression algorithm performed better in yield prediction using fewer data than the simulation model. This study provides a technique to improve tea yield prediction by combining different data sources using a crop simulation model and machine learning algorithms.