Search

Farming is the primary lifestyle in numerous nations, particularly India. Assuming they have never worked, youthful ranchers may not realize which yields to plant and which ones to pick. We're taking care of on this problem, which should be fixed. In the event that you can foresee the right yield and result, you can go with better choices, set aside cash, and hold the gamble of cost changes under wraps. Rather than our framework, which utilizes classification and relapse to sort out crop assortment ideas and result appraises, the ongoing framework isn't being utilized. ML strategies ought to be utilized in the cultivation business to foresee the quantity of harvests that will become in view of a bunch of information. The directed ML technique is utilized to take a gander at a dataset and pull information from various sources, like variable unmistakable confirmation, univariate examination, bivariate and multivariate investigation, missing worth frameworks, and so forth. To figure out which program was supposed to give the best return, ML recipes were investigated. While seeing entropy precision, accuracy, recall, F1 Score, sensitivity, specificity, and entropy, the outcomes show that the recommended ML strategy is the most reliable. [ABSTRACT FROM AUTHOR]

Study on pearl millet discrimination in mixed cropping environment was carried out as it forms the major coarse cereal crop in India. The study aims at determining the capabilities of Sentinel1A SAR data and Machine Learning (ML) algorithms for pearl millet discrimination. Six ML algorithms, that is, k-nearest neighbour (k-NN), Decision Tree (DT), support vector machine (SVM), random forest (RF), multi-layer perceptron (MLP) and Naïve Bayes (NB) were evaluated and compared. Meta-classifier using majority voting technique was proposed by ensembling classifiers (RF, SVM and NB) which were diverse and have comparable accuracies. The diversity assessment was conducted using Cochran Q statistics for ensembling purpose. RF classifier (83.76%) using VH polarization produced better result indicating importance of cross-polarization in crop classification. Further, meta-classifier proposed in the study improved the accuracy to 88.15% (approximately by 5%) and class accuracies of pearl millet resulting in improved discrimination of pearl millet in mixed cropping environment. [ABSTRACT FROM AUTHOR]

Sustainable management of groundwater resource is a most critical due to its over exploitation and ascending stress by industrial and socio-economic factors. It is utmost important to manage this precious resource by properly identifying the suitable Groundwater Potential Zones (GPZ). Therefore, the main aim of the present study is to delineate the GPZ in the upper Godavari sub-basin of India by employing different bi-variate, Multi Criteria Decision Making (MCDM), ensembled, and Machine Learning (ML) models. These models include Weight of Evidence (WoE) (bi-variate), Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) (MCDM), Fuzzified Functional Ratio (F-FR) (bi-variate), Extreme Gradient Boosting (XGB) (ML) and Extremely randomized Trees (ET) ML. The ensembled model featured different combination of WoE, TOPSIS and F-FR for mapping the enhanced accuracy in predicting the GPZ. A total of 15 groundwater factors were considered where 75% of the data were selected as training data and the rest 25% as validation data. These data were used to produce the ensembled ML models. The result of the model was plotted in terms of area under curve (AUC)-Receiver Operating Characteristics (ROC) curve and selected best model. The AUC-ROC result of the obtained model was found to be WoE oE models. The result of the model was plotted in termWoE_TOPSIS = 94%, WoE_F-FR = 93%, TOPSIS_F-FR = 94% and WoE_TOPSIS_F-FR = 95%. Results clearly indicate the improved accuracy of ensembled bi-variate and MCDM model over advanced ML model. The predicted statistical properties of the ensembled model also resembled ML models and a high correlation was observed. Thus, the ensembled model can be used over advanced ML models for delineating the GPZ mapping. [ABSTRACT FROM AUTHOR]

The study focuses on the preparation of landslide susceptibility maps in the Kali River valley, Kumaun Himalaya using three machine learning algorithms, namely K-nearest neighbour (KNN), random forest (RF) and extreme gradient boosting (XGB). Fifteen landslide conditioning factors (LCFs) were selected and an inventory of 368 landslides was used for the analysis. Multicollinearity analysis using the variation inflation factor, tolerance and Pearson correlation coefficient (PCC) depicted less to no similarity between all factors. Evaluation of variable importance suggests LCFs such as slope, elevation and distance to thrust contributed significantly and consistently for all three models. Model accuracy was determined and compared using the area under the receiver operating characteristic curve and other statistical signifiers like accuracy, sensitivity, F-measure, accuracy, specificity and recall. The results show that the ensemble algorithms, XGB and RF, yield higher accuracy of approximately 85% compared to the KNN model with 81% accuracy. [ABSTRACT FROM AUTHOR]

The extent of surface-water spread influences the hydrogeology and ecology of waterbodies. Remote sensing technology provides spatial and temporal datasets which aid in mapping the dynamics of surface waterbodies at the regional and global scale. In the present study, temporal changes in the surface area of waterbodies in Telangana, India, were monitored using indices like normalized difference vegetation index, normalized difference water index and modified NDWI and machine learning algorithms like a random forest using Landsat-8 data. Google Earth Engine cloud computing platform was used for processing earth observation data, based on the time series images of Landsat and compared with real-time groundwater levels. The results showed a significant increase (P < 0.01) in both surface-water area and groundwater levels in Telangana, especially after 2015, which we hypothesize could be due to the specialized water conservation project being implemented by the Government of Telangana since 2015. [ABSTRACT FROM AUTHOR]

Stone dust induced risk and vulnerability in the developing nations is very thought-provoking and therefore is necessary to address scientifically to manage it. Identifying vulnerable areas using the robust method is preliminary and essential steps. The present study has intended to delineate Human health vulnerability models (HHVMs) using machine learning algorithms and justify whether ensemble prediction can provide improved results in stone quarry and crushing dominated Middle catchment of Dwarka river basin. Support Vector Machine (SVM), Artificial Neural Network (ANN), Random Forest (RF), Reduced Error Pruning (REP) Tree, Gaussian Process algorithms and ensemble prediction have been applied for HHV modelling. Total 6.9 to 7.37% in cluster 1, 9.11 to 9.6% in cluster 2, 19.63 to 26.79% and 5.34 to 12.85% areas in cluster 3 and 4 is found into very high human health vulnerable class as per the five applied models. REPTree model is found consistent for predicting vulnerability in case of all the clusters followed by GP model. As per the result of RMSE, the RF model is appeared as the most consistent model followed by REPTree. Some of the ensemble prediction models are potential for yielding improved result than individual algorithm. [ABSTRACT FROM AUTHOR]

We have attempted to reproduce the results in Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs, published in JAMA 2016; 316(22), using publicly available data sets. We re-implemented the main method in the original study since the source code is not available. The original study used non-public fundus images from EyePACS and three hospitals in India for training. We used a different EyePACS data set from Kaggle. The original study used the benchmark data set Messidor-2 to evaluate the algorithm's performance. We used another distribution of the Messidor-2 data set, since the original data set is no longer available. In the original study, ophthalmologists re-graded all images for diabetic retinopathy, macular edema, and image gradability. We have one diabetic retinopathy grade per image for our data sets, and we assessed image gradability ourselves. We were not able to reproduce the original study's results with publicly available data. Our algorithm's area under the receiver operating characteristic curve (AUC) of 0.951 (95% CI, 0.947-0.956) on the Kaggle EyePACS test set and 0.853 (95% CI, 0.835-0.871) on Messidor-2 did not come close to the reported AUC of 0.99 on both test sets in the original study. This may be caused by the use of a single grade per image, or different data. This study shows the challenges of reproducing deep learning method results, and the need for more replication and reproduction studies to validate deep learning methods, especially for medical image analysis. Our source code and instructions are available at: . [ABSTRACT FROM AUTHOR]

Arsenic awareness plays a vital role in ensuring the sustainability of arsenic mitigation technologies. Thus far, however, few studies have dealt with the sustainability of such technologies and its associated socioeconomic dimensions. As a result, arsenic awareness prediction has not yet been fully conceptualized. Accordingly, this study evaluated arsenic awareness among arsenic-affected communities in rural India, using a structured questionnaire to record socioeconomic, demographic, and other sociobehavioral factors with an eye to assessing their association with and influence on arsenic awareness. First a logistic regression model was applied and its results compared with those produced by six state-of-the-art machine-learning algorithms (Support Vector Machine [SVM], Kernel-SVM, Decision Tree [DT], k -Nearest Neighbor [ k -NN], Naïve Bayes [NB], and Random Forests [RF]) as measured by their accuracy at predicting arsenic awareness. Most (63%) of the surveyed population was found to be arsenic-aware. Significant arsenic awareness predictors were divided into three types: (1) socioeconomic factors: caste, education level, and occupation; (2) water and sanitation behavior factors: number of family members involved in water collection, distance traveled and time spent for water collection, places for defecation, and materials used for handwashing after defecation; and (3) social capital and trust factors: presence of anganwadi and people's trust in other community members, NGOs, and private agencies. Moreover, individuals' having higher social network positively contributed to arsenic awareness in the communities. Results indicated that both the SVM and the RF algorithms outperformed at overall prediction of arsenic awareness—a nonlinear classification problem. Lower-caste, less educated, and unemployed members of the population were found to be the most vulnerable, requiring immediate arsenic mitigation. To this end, local social institutions and NGOs could play a crucial role in arsenic awareness and outreach programs. Use of SVM or RF or a combination of the two, together with use of a larger sample size, could enhance the accuracy of arsenic awareness prediction. [ABSTRACT FROM AUTHOR]

India's increasing population growth and unsystematic land cover transformation have led to land degradation and a decline in agricultural production. To achieve optimum advantage from the land, proper exploitation of its resources is necessary. Remote sensing, advanced fuzzy logic, and multi-criteria decision-making like analytical hierarchy process (AHP) integrated agricultural land suitability analysis (ALAS) may facilitate identifying and formulating effective agricultural management strategies required for smart agriculture. The present study was conducted to construct India's robust agricultural suitability model by developing hybrid fuzzy logic and the AHP based model. Fourteen topographical, climatological, soil-related, land-use, and land-cover-related factors were prepared and employed to model agricultural suitability. Agricultural suitability models predicted multi-parameters based agricultural suitable zones for the entire country using three fuzzy operators (AND, Gamma 0.8, Gamma 0.9) and a hybrid fuzzy-AHP model. Sensitivity analysis was conducted to test the models' reliability using Moris technique-based global sensitivity analysis, random forest (RF), and correlation coefficient. The best agricultural suitable model was compared with the production of major crops in India. Results showed that 19.8% of the study area was permanently not suitable in the northernmost region, 19.7% was currently not suitable in the northernmost region, while 20.1% and 20.2% areas were predicted as moderately suitable and highly suitable zones, respectively. The rainfall, elevation, slopes, evapotranspiration, and aridity index had a prime influence on the output of the agricultural suitability model. The adopted method and its application processes can analyze agricultural land suitability and recommend optimal farming methods. It is also comprehended as a promising option for meeting food, nutrition, energy, and job demands while still protecting our threatened environment. [Display omitted] • Agriculture land suitability (ALS) mapping for the country has not been yet done due to data scarcity and lack of technology. • e developed and applied fuzzy-AHP and fuzzy logic-based ALS models, as well as several sensitivity analyses. • 20.2% and 19.78% area were identified as highly suitable and permanently unsuitable for agriculture. • The integrated fuzzy-AHP based ALS model was found to be the best model for ALS mapping. • A robust ALS model could aid agricultural decisions that support smart agricultural practices with greater production. [ABSTRACT FROM AUTHOR]

We investigate the performance of existing state-of-the-art rule induction and tree algorithms, namely Single Conjunctive Rule Learner, Decision Table, M5 Model Tree, Decision Stump and REPTree. Downscaling models are developed using these algorithms to obtain projections of mean monthly precipitation to lake-basin scale in an arid region in India. The effectiveness of these algorithms is evaluated through application to downscale the predictand for the Lake Pichola region in Rajasthan state in India, which is considered to be a climatically sensitive region. The predictor variables are extracted from (1) the National Centre for Environmental Prediction (NCEP) reanalysis dataset for the period 1948-2000 and (2) the simulations from the third-generation Canadian Coupled Global Climate Model (CGCM3) for emission scenarios A1B, A2, B1 and COMMIT for the period 2001-2100. M5 Model Tree algorithm was found to yield better performance among all other learning techniques explored in the present study. The precipitation is projected to increase in future for A2 and AIB scenarios, whereas it is least for B1 and COMMIT scenarios using predictors. [ABSTRACT FROM AUTHOR]

The drought induced vulnerability is owed much to rapid modernization, climate extremes, and over exploitation of natural resources. However, a natural phenomenon, the drought is amplified by anthropogenic activities that in its enormity influences water availability, agricultural productivity, ecosystem, groundwater storage. The Karnataka state of India is frequently affected by the drought that causes huge loss in agricultural sector and other allied sectors. Therefore, it is essential to measure the vulnerability status for the better management of natural resources in the state of Karnataka. No advanced models are being used yet to portray the drought vulnerability status. Different advanced machine learning models are effective in predicting various physical vulnerabilities. The aim of this study was to use sophisticated machine learning models to precisely define relative drought vulnerability. In that endeavour, it used two advanced machine-learning algorithms (MLAs), namely, Bagging and Artificial Neural Network (ANN) which are still not used in this field. Twenty-six meteorological and socio-economical parameters were considered to find the most drought vulnerable areas. The predisposing parameters were classified as resilience (7 parameters), sensitivity (9 parameters), and exposure (10 parameters). The researchers have produced drought vulnerability maps for overall condition, resilience, sensitivity, and exposure. The relative drought vulnerability maps (RDVMs) clearly show that 40.87%–52.03% of areas fall under very high vulnerability, which is situated in the central and eastern parts of the state. The prediction capacity of newly built models was judged with efficiency, root mean square error (RMSE), true skill statistics (TSS), Friedman and Wilcoxon rank test, and area under the curve (AUC) of receiver operating characteristic (ROC). All of them showed satisfactory results - the RMSE value of 0.32 and 0.33, TSS values of 0.82 and 0.81, and AUC values of 86.50% and 84.20% as obtained by ANN and bagging models, respectively. The produced RDVMs demonstrate the urgency of policy interventions to minimize vulnerability in prioritized areas. [Display omitted] • Drought vulnerability was assessed by Bagging and Artificial Neural Network (ANN). • Factors of exposure, sensitivity and resilience were standardized by fuzzy method. • ANN model achieved the highest accuracy (86.50%) in drought vulnerability mapping. • There is difference amid bagging and ANN models as per Wilcoxon and Friedman tests. • Nearly 61% of the study area has very high to high drought vulnerability. [ABSTRACT FROM AUTHOR]

• Livelihood Vulnerability state was modelled. • The Support Vector Machine was considered as the best algorithm. • Bank erosion rate appeared as influencing parameters for LVS. • 39% to 53% area under high to very high vulnerability of LVS. • Exposure model was highly correlated (r = 0.87) with overall LVS. River island (locally known as charland) in river Ganges from Rajmahal hill to Farakka barrage of India is now under human habitat dominated by the environmentally evicted people triggered by bank erosion, but these are under different physical vulnerability like bank erosion, flooding etc. Considering the physical inconvenience, and inaccessibility, the present work intended to model the livelihood vulnerability state (LVS) by using advance machine learning algorithms, like Artificial neural network (ANN), Random forest (RF), Random subspace (RS) and Support vector machine (SVM). For LVS modelling, field and remote sensing based 26 parameters were selected. We classified the parameters as exposure (11 parameters), sensitivity (4 parameters) and adaptive capacity (11 parameters). We modelled LVS for overall condition, exposure, adaptive capacity, and sensitivity. Application of these algorithms in this field is unique and its robustness and precision in result is highly satisfactory. LVS models clearly identified 39% to 53% of areas having high to very high vulnerability and these are located at the edge of the charlands. Among the models, SVM outperformed as per the result of accuracy assessment. Therefore, it can be treated as a representative algorithm for LVS modelling. Among the 26 parameters, bank erosion, unhygienic condition, and Below Poverty Level (BPL) household parameters were found as highly dominating based on the findings of information and gain ratio. The correlation with LVS and three individual models (exposure, adaptive capacity, and sensitivity) exhibited that the Exposure model was highly correlated (r = 0.87) with high statistical significance (0.001 level). [ABSTRACT FROM AUTHOR]

• TSI increased from 18–22 to 44–54 showing deterioration of trophic state. • 30% of area comes under high vulnerable zone in the pre-dam period. • 54% of area comes under high vulnerable zone in the post-dam period. • RBF model is the best model of habitat vulnerability (AUC-0.877 and 0.868). • A strong spatial relation between TSI and habitat vulnerability is found. Damming over the river remarkably alters the downstream hydrological and ecological state of the river and riparian wetlands. Considering this, the present work intended to explore the habitat quality and the trophic state index (TSI) of the wetland in Tangan river basin of India and Bangladesh. The spatial linkages between habitat quality and TSI was also assessed. Random forest (RF), Radial basis function neural network (RBF) and Artificial neural network (ANN) algorithms based habitat vulnerability models were constructed based on eight proxy data layers, which are mainly related to hydrology. The ANN and RBF models were found as the best representative. In the pre-dam period, about 30% area was under high and very high habitat vulnerability, while it was increased to 54% after damming. TSI value in the post-dam period was found significantly higher (44–54) in comparison to pre-dam phase (18–22). It was also identified that vulnerable habitat areas were more susceptible to poorer water quality. Hence, in water quality and ecosystem related data sparse conditions, the proxy parameters can be used effectively for habitat vulnerability modelling. Furthermore, results clearly demonstrated that damming has deteriorated the habitability and trophic state of the wetland. To restrain the growing impact, ecological flow maintenance to the dam downstream river and riparian wetland is essential. [ABSTRACT FROM AUTHOR]

• An integrated approach of spectral enhancement techniques and machine learning models for an accurate mapping of spectrally similar rock types. • The support vector machine outperforms other methods i.e. random forest and linear discriminant analysis for rock type classification. • SVM appeared to be less sensitive to the number of samples and mislabeling in training datasets as compared to other machine learning models. • The high-resolution lithological map with distinct litho-contacts of amphibolite, metabasalt, and granite is important for gold mineralization studies. In this study, we proposed an automated lithological mapping approach by using spectral enhancement techniques and Machine Learning Algorithms (MLAs) using Airborne Visible Infrared Imaging Spectroradiometer-Next Generation (AVIRIS-NG) hyperspectral data in the greenstone belt of the Hutti area, India. We integrated spectral enhancement techniques such as Principal Component Analysis (PCA) and Independent Component Analysis (ICA) transformation and different MLAs for an accurate mapping of rock types. A conjugate utilization of conventional geological map and spectral enhancement products derived from ASTER data were used for the preparation of a high-resolution reference lithology map. Feature selection and extraction methods were applied on the AVIRIS-NG data to derive different input dataset such as (a) all spectral bands, (b) shortwave infrared bands, (c) Joint Mutual Information Maximization (JMIM) based optimum bands, and (d) optimum bands using PCA, to choose optimum input dataset for automated lithological mapping. The comparative analysis of different MLAs shows that the Support Vector Machine (SVM) outperforms other Machine Learning (ML) models. The SVM achieved an Overall Accuracy (OA) and Kappa Coefficient (k) of 85.48% and 0.83, respectively, using JMIM based optimum bands. The JMIM based optimum bands were more suitable than other input datasets to classify most of the lithological units (i.e. metabasalt, amphibolite, granite, acidic intrusive and migmatite) within the study area. The sensitivity analysis performed in this study illustrates that the SVM is less sensitive to the number of samples and mislabeling in the model training than other MLAs. The obtained high-resolution classified map with accurate litho-contacts of amphibolite, metabasalt, and granite can be coupled with an alteration map of the area for targeting the potential zone of gold mineralization. [ABSTRACT FROM AUTHOR]