Smart Nutrient Decisions: DRIS–GIS Integration for Precision Oil Palm Plantation Management

This dataset comprises the results of leaf nutrient analysis and DRIS (Diagnosis and Recommendation Integrated System) index calculations from 3,700 georeferenced sampling points across oil palm plantations in North Sumatra, Indonesia. It provides a comprehensive view of the plant nutrient status based on five key macronutrients: nitrogen (N), phosphorus (P), potassium (K), calcium (Ca), and magnesium (Mg). The nutrient concentrations, derived from standardized laboratory analyses, are expressed as percentages of dry leaf tissue.

Beyond individual nutrient values, the dataset integrates the DRIS approach, which evaluates the balance among nutrients rather than absolute levels. For each sample, actual nutrient ratios (e.g., N/P, N/K, N/Ca, N/Mg) are calculated and compared against standard ratios derived from high-yielding reference populations. These standard ratios are included in the dataset and serve as benchmarks for assessing nutritional balance. Based on the deviation from these standards, each nutrient pair is classified as "Below Optimum," "Optimum," or "Above Optimum," allowing practitioners to quickly identify relative deficiencies or excesses.

Key outputs of the DRIS methodology are the nutrient indices (Index_N, Index_P, etc.), which quantify the extent to which each nutrient limits or exceeds optimal balance. A positive DRIS index indicates a relative excess, while a negative index points to a deficiency. These indices provide a hierarchy of nutrient limitations for each sample and are more informative than conventional threshold-based interpretations, which can overlook hidden deficiencies caused by nutrient interactions.

Supporting parameters such as the standard deviations of each nutrient ratio are also provided, ensuring that DRIS calculations are normalized and statistically meaningful. This structure allows for nuanced interpretations of nutrient imbalances across varying plantation conditions.

This dataset is valuable for plantation managers, agronomists, and researchers focused on precision agriculture. It enables site-specific fertilizer recommendations, early diagnosis of nutrient limitations, and long-term monitoring of soil-plant nutrient dynamics. Furthermore, it lays the groundwork for spatial modeling, decision support systems, and integration with remote sensing or AI-based tools to enhance nutrient use efficiency and productivity in oil palm cultivation.