No packages match

xaiHydro - Explainable AI Tools for Hydro-Climate Modelling

Provides a unified workflow for applying Explainable Artificial Intelligence (XAI) methods to hydro-climate predictive models. Functions implement a permutation-based Monte Carlo SHAP estimator (Strumbelj and Kononenko (2014) <doi:10.1007/s10115-013-0679-x>; Lundberg and Lee (2017) <doi:10.48550/arXiv.1705.07874>), a self-contained locally weighted linear surrogate LIME (Ribeiro et al. (2016) <doi:10.1145/2939672.2939778>), and Partial Dependence Plots with Accumulated Local Effects (Friedman (2001) <doi:10.1214/aos/1013203451>; Apley and Zhu (2020) <doi:10.1111/rssb.12377>) with hydrology-specific visualisations and interpretation utilities. Supports any model object compatible with the 'DALEX' explainer interface (Biecek (2018) <doi:10.18637/jss.v097.i01>), including random forests, gradient boosting, and neural networks trained on streamflow, drought indices, flood risk, or evapotranspiration data. Hydrology-standard performance metrics Nash-Sutcliffe Efficiency (NSE, Nash and Sutcliffe (1970) <doi:10.1016/0022-1694(70)90255-6>) and Kling-Gupta Efficiency (KGE, Gupta et al. (2009) <doi:10.1016/j.jhydrol.2009.08.003>) are computed alongside standard regression metrics. Designed to accompany the book chapter: Islam, S., Dheeraj, A., Ali, S., Kaushal, R. and Venkatesh, G. (2026). Explainable Artificial Intelligence for Hydro-Climatic Modelling: Methods, Applications, and Implementation Using the xaiHydro R Package. In Chandniha, S. K. et al. (Eds.), Hydro-Climate Analytics: Remote Sensing, AI and Geospatial Modelling. Springer.

Last updated

3.00 score 16 downloads

NRMstatsML - Statistical and Machine Learning Engine for Long-Term Natural Resource Management Data

A comprehensive toolkit for statistical and machine learning-based analysis of long-term Natural Resource Management (NRM) datasets. Integrates formula-driven approaches, statistical inference, and machine learning (ML) models for advanced analytics. Modules cover trend and structural analysis (Mann-Kendall test, slope estimation, Chow test, structural break detection), multivariate system modelling (Partial Least Squares (PLS), Structural Equation Modelling (SEM)), response curve optimisation, time-series forecasting (Autoregressive Integrated Moving Average (ARIMA), hybrid models), panel data and treatment effects (Difference-in-Differences (DiD), causal machine learning), uncertainty and sensitivity analysis (bootstrap, Monte Carlo, Bayesian), and automated model selection and performance comparison. Designed for long-term datasets covering soil, water, crop, and climate domains. Key references: Mann and Kendall (1945) <doi:10.2307/1907187>; Sen (1968) <doi:10.1080/01621459.1968.10480934>; Bai and Perron (2003) <doi:10.1002/jae.659>; Rosseel (2012) <doi:10.18637/jss.v048.i02>; Croissant and Millo (2008) <doi:10.18637/jss.v027.i02>.

Last updated

3.00 score 220 downloads

rainerosr - Calculate Rainfall Intensity and Erosivity Indices

Calculates I30 (maximum 30-minute rainfall intensity) and EI30 (erosivity index) from rainfall breakpoint data. Supports multiple storm events, rainfall validation, and visualization for soil erosion modeling and hydrological analysis. Methods are based on Brown and Foster (1987) <doi:10.13031/2013.30422>, Wischmeier and Smith (1978) "Predicting Rainfall Erosion Losses: A Guide to Conservation Planning" <doi:10.22004/ag.econ.171903>, and Renard et al. (1997) "Predicting Soil Erosion by Water: A Guide to Conservation Planning with the Revised Universal Soil Loss Equation (RUSLE)" (USDA Agriculture Handbook No. 703).

Last updated

3.00 score 318 downloads

climatestatsr - Statistical Tools for Climate Change Analysis

A comprehensive collection of statistical functions for climate change research. Provides tools for temporal trend detection based on the Mann-Kendall (MK) test (Mann 1945 <doi:10.2307/1907187>; Kendall 1975, ISBN:0852641990) and Sen's slope (Sen 1968 <doi:10.2307/2285891>), spatial autocorrelation using Moran's I (Moran 1950 <doi:10.2307/2332142>), extreme value analysis using the Generalised Extreme Value (GEV) distribution and Peaks-Over-Threshold (POT) method (Coles 2001 <doi:10.1007/978-1-4471-3675-0>), standardised drought indices including the Standardised Precipitation Index (SPI; McKee et al. 1993) and the Standardised Precipitation Evapotranspiration Index (SPEI; Vicente-Serrano et al. 2010 <doi:10.1175/2009JCLI2909.1>), and formal detection-attribution methods via optimal fingerprint regression and Empirical Orthogonal Function (EOF) analysis (Allen and Tett 1999 <doi:10.1007/s003820050291>), and apparent temperature via the heat index (Steadman 1979 <doi:10.1175/1520-0450(1979)018%3C0861:TAOSPI%3E2.0.CO;2>). Suitable for both station-level time series and gridded climate fields.

Last updated

2.70 score 348 downloads

SQIpro - Comprehensive Soil Quality Index Computation and Visualization

Provides a comprehensive, modular framework for computing the Soil Quality Index (SQI) using six established methods: Linear Scoring (Doran and Parkin, 1994, <doi:10.2136/sssaspecpub35.c1>), Regression-based (Masto et al., 2008, <doi:10.1007/s10661-007-9697-z>), Principal Component Analysis-based (Andrews et al., 2004, <doi:10.2136/sssaj2004.1945>), Fuzzy Logic, Entropy Weighting (Shannon, 1948, <doi:10.1002/j.1538-7305.1948.tb01338.x>), and TOPSIS (Hwang and Yoon, 1981, <doi:10.1007/978-3-642-48318-9>). Implements four variable scoring functions: more-is-better, less-is-better, optimum-value, and trapezoidal, following Karlen and Stott (1994, <doi:10.2136/sssaspecpub35.c4>). Includes automated Minimum Data Set selection via Principal Component Analysis with Variance Inflation Factor filtering (Kaiser, 1960, <doi:10.1177/001316446002000116>), one-way ANOVA with Tukey HSD post-hoc tests, leave-one-out sensitivity analysis, and publication-quality visualization using 'ggplot2'.

Last updated

2.70 score 326 downloads

soiltillr - Analyse Soil Tillage Depth and Erosion Over Time

Provides tools to record, validate, and analyse soil tillage depth and erosion across years and field treatments. Includes functions for year-wise tillage operation summaries, erosion depth tracking, compaction detection, soil loss estimation, and visualisation of temporal changes in tillage and erosion profiles. Methods follow Lal (2001) <doi:10.1201/9780203739280> and Renard et al. (1997) "Predicting Soil Erosion by Water: A Guide to Conservation Planning with the Revised Universal Soil Loss Equation (RUSLE)" <https://ntrl.ntis.gov/NTRL/dashboard/searchResults/titleDetail/PB97153704.xhtml>.

Last updated

2.70 score 203 downloads

llmclean - LLM-Assisted Data Cleaning with Multi-Provider Support

Detects and suggests fixes for semantic inconsistencies in data frames by calling large language models (LLMs) through a unified, provider-agnostic interface. Supported providers include 'OpenAI' ('GPT-4o', 'GPT-4o-mini') <https://platform.openai.com>, 'Anthropic' ('Claude') <https://www.anthropic.com>, 'Google' ('Gemini') <https://ai.google.dev>, 'Groq' (free-tier 'LLaMA' and 'Mixtral') <https://groq.com>, and local 'Ollama' models <https://ollama.com>. The package identifies issues that rule-based tools cannot detect: abbreviation variants, typographic errors, case inconsistencies, and malformed values. Results are returned as tidy data frames with column, row index, detected value, issue type, suggested fix, and confidence score. An offline fallback using statistical and fuzzy-matching methods is provided for use without any application programming interface (API) key. Interactive fix application with human review is supported via 'apply_fixes()'. Methods follow de Jonge and van der Loo (2013) <https://cran.r-project.org/doc/contrib/de_Jonge+van_der_Loo-Introduction_to_data_cleaning_with_R.pdf> and Chaudhuri et al. (2003) <doi:10.1145/872757.872796>.

Last updated

2.30 score 201 downloads

agriReg - Linear and Nonlinear Regression for Agricultural Data

Fit, compare, and visualise linear and nonlinear regression models tailored to field-trial and dose-response agricultural data. Provides S3 classes for mixed-effects models (via 'lme4'), nonlinear growth curves (logistic, 'Gompertz', asymptotic, linear-plateau, quadratic), and four/five-parameter log-logistic dose-response models (via 'drc'). Includes automated starting-value heuristics, goodness-of-fit statistics, residual diagnostics, and 'ggplot2'-based visualisation. Methods are based on Bates and Watts (1988, ISBN:9780471816430), Ritz and others (2015) <doi:10.1371/journal.pone.0146021>, and Bates and others (2015) <doi:10.18637/jss.v067.i01>.

Last updated

2.30 score 291 downloads

llmimpute - Missing Data Imputation via Language Models and Statistics

Provides missing data imputation through two complementary engines: a large language model engine that communicates with the 'Anthropic' 'Claude' application programming interface for context-aware semantic imputation, and a fully self-contained offline engine implementing nineteen statistical and machine learning algorithms entirely in base R with no additional package dependencies. Offline methods include mean, median, mode, last observation carried forward, next observation carried backward, hot-deck, predictive mean matching, k-nearest neighbours, ordinary least-squares regression, Lasso with coordinate descent, Ridge with closed-form solution, Bayesian Ridge regression with evidence approximation following MacKay (1992), support vector regression with a radial basis function kernel, classification and regression trees, random forests, gradient boosting, iterative random forest imputation, principal component analysis imputation via iterative singular value decomposition, and nuclear-norm minimisation via singular value thresholding. When no API key is available the package automatically falls back to the offline engine, ensuring full operation in environments without internet access. Every imputed value is accompanied by a confidence score and a plain-language reasoning string, producing reproducible audit trails. The automatic method selector chooses the best algorithm per column based on data type, skewness, missingness rate, and inter-column correlations.

Last updated

2.00 score 273 downloads

ensembleML - Unified Interface for Ensemble Machine Learning Methods

Provides a clean, unified interface for training, predicting, and evaluating ensemble machine learning models including Random Forest, Gradient Boosting ('XGBoost'), 'AdaBoost', and 'Bagging'. All algorithms share a consistent API: em_fit(), em_predict(), em_evaluate(), and em_tune(). Includes built-in cross-validation, feature importance, calibration diagnostics, partial dependence plots, and model comparison utilities. Methods: Breiman (2001) <doi:10.1023/A:1010933404324>; Chen and Guestrin (2016) <doi:10.1145/2939672.2939785>; Freund and Schapire (1997) <doi:10.1006/jcss.1997.1504>; Breiman (1996) <doi:10.1007/BF00058655>.

Last updated

2.00 score 3 scripts 387 downloads

NRMSampling - Sampling Design and Estimation Methods for Natural Resource Management

Provides functions for probability and non-probability sampling design, sample selection, and population estimation tailored to natural resource management. Probability methods include simple random sampling, stratified sampling, systematic sampling, cluster sampling, and probability-proportional-to-size sampling. Non-probability methods include convenience, judgement-based, and quota sampling. Estimation functions cover means, totals, ratio estimators, regression estimators, and the unequal-probability estimator of Horvitz and Thompson (1952, <doi:10.2307/2280784>) for unequal-probability designs. Utilities support biomass, soil-loss, and carbon-stock estimation from field plots. Spatial extensions provide random, systematic, stratified, and raster-weighted sampling within geographic polygons using the 'sf' and 'terra' packages, with extraction of remote-sensing covariates at sample locations. Applications include forest inventory, soil erosion monitoring, watershed studies, and ecological field surveys.

Last updated

2.00 score 301 downloads

swcEcon - Economic Analysis of Soil and Water Conservation Measures in Watersheds

Provides functions and benchmark datasets for the economic appraisal of soil and water conservation (SWC) measures in watershed development projects. Implements benefit-cost ratio (BCR), net present value (NPV), internal rate of return (IRR) via the bisection method of Brent (1973, ISBN:9780130223715), modified BCR, marginal rate of return using the CIMMYT (1988, ISBN:9686127127) method, payback period, soil loss economic valuation via the Universal Soil Loss Equation of Wischmeier and Smith (1978, ISBN:0160016258), groundwater recharge valuation, employment generation ratio, sensitivity analysis, switching value analysis, and Monte Carlo simulation. Six datasets are included: state-wise BCR benchmarks from NABARD (2019) watershed evaluations, USLE erodibility parameters for Indian soil orders from NBSS and LUP, rainfall erosivity for twenty Indian districts from IMD data, SWC unit cost norms from PMKSY-WDC (GoI 2015), and two hypothetical datasets for illustration. Methods follow Gittinger (1982, ISBN:9780801825439) and Squire and van der Tak (1975, ISBN:9780801816697).

Last updated

2.00 score 289 downloads

CREDS - Calibrated Ratio Estimator under Double Sampling Design

Population ratio estimator (calibrated) under two-phase random sampling design has gained enormous popularity in the recent time. This package provides functions for estimation population ratio (calibrated) under two phase sampling design, including the approximate variance of the ratio estimator. The improved ratio estimator can be applicable for both the case, when auxiliary data is available at unit level or aggregate level (eg., mean or total) for first phase sampled. Calibration weight of each unit of the second phase sample was calculated. Single and combined inclusion probabilities were also estimated for both phases under two phase random [simple random sampling without replacement (SRSWOR)] sampling. The improved ratio estimator's percentage coefficient of variation was also determined as a measure of accuracy. This package has been developed based on the theoretical development of Islam et al. (2021) and Ozgul (2020) <doi:10.1080/00949655.2020.1844702>.

Last updated

1.71 score 51 scripts 216 downloads

agriDQ - Data Quality Checks and Statistical Assumption Testing for Agricultural Experiments

Provides a comprehensive pipeline for data quality checks and statistical assumption diagnostics in agricultural experimental data. Functions cover outlier detection using Interquartile Range (IQR) fence, Z-score, modified Z-score (Hampel identifier), Grubbs test and Dixon Q-test with consensus flagging; missing data pattern analysis and mechanism classification (Missing Completely At Random/Missing At Random/Missing Not At Random (MCAR/MAR/MNAR)) via Little's test; normality testing using Shapiro-Wilk, Anderson-Darling, Kolmogorov-Smirnov, Lilliefors, Pearson chi-square and Jarque-Bera tests; homogeneity of variance via Bartlett, Levene and Fligner-Killeen tests; independence of errors via Durbin-Watson, Breusch-Godfrey and Wald-Wolfowitz runs tests; experimental design validation for Completely Randomised Design (CRD), Randomised Complete Block Design (RCBD), Latin Square Design (LSD) and factorial designs; qualitative variable consistency checks; and automated HyperText Markup Language (HTML) report generation. Designed to align with Findable, Accessible, Interoperable and Reusable (FAIR) data principles. Methods follow Gomez and Gomez (1984, ISBN:978-0471870920) and Montgomery (2017, ISBN:978-1119492443).

Last updated

1.70 score 403 downloads