The research addresses a pressing challenge in modern horticulture. High-density orchards, which pack dwarfing rootstocks and slender trees into tight rows to maximize early returns, demand intensive inputs of fertilizers and agrochemicals. Input costs have been climbing steadily, while environmental scrutiny of conventional chemical programs has intensified. Growers and scientists alike have been searching for eco-friendly alternatives that can sustain productivity without compromising fruit quality or soil health. Plant biostimulants, substances that modulate plant growth and stress responses rather than simply feeding crops, have emerged as one of the most promising candidates, and weed-derived formulations are an especially attractive class because their raw material is abundant, cheap and otherwise destined for disposal.

What makes weeds chemically interesting, the authors note, is their diverse arsenal of bioactive secondary metabolites. Plants that thrive in harsh, competitive environments often accumulate phenolics, alkaloids, terpenoids and other compounds that, when extracted and applied to crops, can influence hormone signaling, nutrient uptake and stress tolerance. Rather than treating these formulations as a generic tonic, the Indian team hypothesized that timing matters enormously. A tree’s needs shift dramatically across its phenological calendar, from budbreak and flowering through fruit set, cell expansion and ripening, so a spray that helps at one stage may be irrelevant or wasteful at another. Their experiment was designed to test whether matching applications to nine distinct phenological stages would unlock the full potential of the bio-formulations.

The field trials were conducted during 2024 and 2025 at two contrasting orchard sites in the apple-growing hills of Himachal Pradesh. One site, at Nauni, used trees on the dwarfing EMLA9 rootstock, while the other, at Kandaghat, used trees on the more vigorous MM111 rootstock. Both orchards were managed under high-density systems, the very conditions where input costs and tree stress tend to be most acute. The researchers employed a split-plot design with four replications, a statistically robust layout that allowed them to separate treatment effects from site and block variation. Five treatments were compared, each consisting of a different combination of stage-specific bio-formulation applications, alongside a control that received only water sprays.

The standout treatment, designated T1, involved sequential applications of the bio-formulations across all nine phenological stages, effectively accompanying the tree through its entire productive cycle. The results were striking. Fruit set rose from 38.56 percent in the control trees to 44.67 percent in the T1 trees, a meaningful gain in a crop where every percentage point of set translates directly into marketable fruit. More dramatically, yield per tree climbed from 2.81 kilograms to 4.83 kilograms, an increase of roughly 72 percent. For high-density growers calculating returns per hectare, a jump of that magnitude, achieved without synthetic agrochemical inputs, represents a potentially transformative economics shift.

Fruit quality, the attribute that ultimately determines price and consumer acceptance, improved alongside quantity. Apples from treated trees were measurably firmer, registering 7.67 kilograms per square centimeter of flesh resistance compared with 6.58 in controls, a difference that matters for shelf life, transport tolerance and the crisp bite that ‘Gala’ consumers expect. Total soluble solids, the standard proxy for sweetness measured in degrees Brix, rose from 10.83 to 12.44, while total sugar content increased from 9.91 percent to 11.19 percent. Taken together, these figures describe fruit that is not only more abundant but also sweeter, firmer and better suited to the demands of long-distance supply chains.

Beneath the visible improvements in the fruit, the leaf analysis revealed a physiological mechanism at work. Concentrations of the three primary macronutrients in the foliage all rose significantly relative to the control: nitrogen increased by 29.2 percent, phosphorus by 50.0 percent and potassium by 18.6 percent. Phosphorus, often the most limiting nutrient in hill soils, plays central roles in energy transfer and flowering, while potassium governs fruit size, sugar accumulation and firmness. The pattern of nutrient enhancement aligns neatly with the observed gains in fruit set, sweetness and texture, suggesting that the bio-formulations improved the trees’ ability to acquire and mobilize nutrients rather than merely stimulating growth at the expense of quality.

To test whether these improvements were statistically coherent rather than a collection of coincidental effects, the team applied two complementary analytical tools. Pearson’s correlation analysis revealed significant positive associations among vegetative growth, nutrient status, yield and fruit quality traits, indicating that the treatments lifted the entire performance profile of the trees in concert. Principal component analysis then condensed the many measured variables into a few underlying dimensions, and the results were unusually clean: the first two components together explained 97.57 percent of the total variation, with the first component alone accounting for 68.96 percent. When a small number of components capture nearly all the variation in an experiment, it signals that the treatments produced a strong, systematic biological response rather than scattered, noise-driven differences.

The implications extend well beyond one cultivar and one growing season. Because the formulations are derived from weeds, they offer a circular-economy twist: plants that compete with crops for water and nutrients can be harvested, processed and returned to the orchard as a growth-enhancing spray. That could reduce both the labor of weed management and the expenditure on synthetic inputs, a double saving for smallholder growers in the Himalayan apple belt who face some of the steepest production costs in the industry. The phenology-based protocol also gives growers a practical scheduling framework, since the nine application stages correspond to observable milestones such as budbreak, bloom and fruit development that are already part of standard orchard record-keeping.

Cautions remain before the practice can be widely recommended. The study covered two seasons at two sites on a single cultivar, and the published version is an early-release, peer-reviewed accepted manuscript that will be replaced by a final Version of Record. Follow-up work will need to establish how the formulations perform across different rootstocks, climates and cultivars, and to characterize the active compounds responsible for the effects. Nevertheless, the core result stands on firm statistical ground: timed applications of weed-derived bio-formulations increased fruit set, boosted yield by more than 70 percent, improved firmness and sweetness, and elevated leaf nitrogen, phosphorus and potassium in high-density ‘Gala Schniga Schnico’ apple orchards. If those gains hold at scale, the humble weeds at the edge of the orchard may become one of its most valuable assets.

Subject of Research: Phenology-based application of weed-derived plant biostimulants in high-density apple orchards

Article Title: Phenology-based application of weed-derived bio-formulations enhances growth, yield, fruit quality and leaf nutrient status of ‘Gala Schniga Schnico’ apple under high-density orchard systems

Article References: Kumar, P., Ladon, T., Sharma, A., Devi, M., Vikram, A. K., Chauhan, J. K., & Rana, R. K. (2026). Phenology-based application of weed-derived bio-formulations enhances growth, yield, fruit quality and leaf nutrient status of ‘Gala Schniga Schnico’ apple under high-density orchard systems. BMC Plant Biology. https://doi.org/10.1186/s12870-026-09504-8

Image Credits: AI Generated

DOI: 10.1186/s12870-026-09504-8

Keywords: weed-derived bio-formulations, plant biostimulants, phenology, apple production, high-density orchards, fruit quality, fruit set, leaf nutrient status, sustainable horticulture, Gala apple, foliar application, BMC Plant Biology

The research team, led by Jie Zhou and Jianqiang He, built and compared five different machine learning models for predicting whether a late-spring frost event would strike apple orchards during the flowering period: Random Forest, Support Vector Machine, Extreme Gradient Boosting (XGBoost), a Multilayer Perceptron neural network, and a Long Short-Term Memory (LSTM) network. Crucially, they went beyond the meteorological data that most earlier studies relied on, adding spatial geographic variables including latitude, longitude, altitude, slope, and aspect to the predictor set. The study area covered China’s four major apple-growing regions: the Bohai Bay region, the Loess Plateau, the Southwestern Cool Highland, and Xinjiang. The Loess Plateau alone accounts for about 57.2 percent of national apple planting area, while the Bohai Bay region contributes roughly 26.9 percent.

The technical rationale for adding geography is rooted in the physics of frost formation. Frost at its core is a short-term low-temperature disaster in which plant tissues drop below 0 degrees Celsius, either through radiative cooling under clear, calm, high-pressure conditions or through advective frost when masses of cold air push temperatures below the frost point. The near-surface temperatures that determine whether buds, flowers, and young leaves freeze vary dramatically with terrain. Cold, dense air drains downslope at night and pools in narrow valleys and low-lying flats, while higher and more convex positions rarely freeze. Slope orientation matters too, because south-facing slopes in the Northern Hemisphere intercept more solar radiation and stay warmer than shaded north-facing slopes. A model blind to these spatial features is structurally incapable of capturing where frost will actually occur.

To train and test the models, the researchers compiled historical frost-damage records from 179 representative apple-growing sites in 2018 and 86 sites in 2020, drawing on the China Meteorological Disaster Management System, provincial meteorological bureaus, disaster yearbooks, and field investigations reported in the scientific literature. Frost severity was harmonized according to the Chinese Meteorological Industry Standard for flowering-stage frost damage in Fuji apples, which classifies injury as mild, moderate, or severe based on visible damage to petals, anthers, pistils, and ovaries and corresponding frost-injury rates. For the binary classification task, all severity levels were merged into a single frost-occurrence class, while non-frost samples were strictly defined as synchronous observations from the same sites and dates where no damage occurred. Predictor variables passed rigorous screening: average temperature was removed because its correlation with minimum temperature exceeded 0.7, and variance inflation factor tests confirmed that the remaining ten variables were free of problematic multicollinearity.

The results were striking. When the geographic variables were added to the meteorological set, every model improved. Overall accuracy rose to 0.900 for both Random Forest and XGBoost, 0.895 for the attention-enhanced LSTM, 0.882 for the Support Vector Machine, and 0.834 for the Multilayer Perceptron. The Random Forest model achieved the best discrimination overall, with an area under the receiver operating characteristic curve of 0.96 and a true positive rate of 0.914, meaning it correctly identified more than nine in ten actual frost events. XGBoost posted the lowest false alarm rate at 0.026, and the Support Vector Machine raised its true positive rate from 0.813 to 0.870 once geographic information was included. The team also introduced an LSTM variant augmented with a channel attention mechanism, which adaptively reweights input feature channels so the network emphasizes the most informative predictors. This LSTM-CAM model lifted overall accuracy from 0.861 to 0.895 and the true positive rate from 0.616 to 0.764 compared with a vanilla LSTM, demonstrating that attention-guided feature selection meaningfully improves multi-source data fusion.

Perhaps the most consequential methodological innovation was the application of SHAP, or Shapley Additive exPlanations, to open the black box. Derived from cooperative game theory, SHAP calculates the average marginal contribution of each input feature across all possible feature coalitions, yielding values that quantify exactly how much each variable pushed a given prediction toward or away from frost. Positive Shapley values indicate features that increased predicted frost probability, while negative values indicate suppressive effects. Crucially, SHAP delivers both global explanations, summarizing each variable’s average importance across all samples, and local explanations, revealing how individual predictions were formed. For farmers and foresters who must act on model outputs, this transparency transforms an opaque statistical verdict into an interpretable physical story.

What did the explanations reveal? Across every model, minimum temperature emerged as the single most influential predictor of late-spring frost, an intuitive but now quantified result. Solar radiation ranked second in the Random Forest and LSTM-CAM models: sunny days heat and charge the soil with energy that is then radiated away after sunset, so low daytime radiation signals a greater risk of nocturnal radiative cooling and frost. Wind speed also shaped the predictions, because strong winds mix warm air aloft down to the surface and disrupt the stagnant cold-air pooling that otherwise lets temperatures plummet in valleys and depressions. Among geographic factors, latitude was the leading driver in the Random Forest model, while altitude ranked highly in the Support Vector Machine and LSTM-CAM models, consistent with evidence that trees at higher elevations face rising frost exposure as warming advances spring phenology faster than frost dates retreat. Slope and aspect, being purely local terrain features, contributed less at regional scales but produced substantial local SHAP responses in specific conditions.

The framework’s real-world credibility was tested by asking the models to reproduce the severe 2018 frost disaster spatially across the four growing regions. All models captured the general pattern of the disaster, but with telling differences in spatial realism. The Random Forest model showed the highest spatial agreement with observed frost-damage rates on apple central flowers, correctly delineating the high-risk belts across the Loess Plateau and parts of the Bohai Bay region while assigning low probabilities to the comparatively unscathed Xinjiang and Southwestern Cool Highland regions. The Support Vector Machine and XGBoost models produced more fragmented high-risk zones and overestimated frost in areas like parts of Liaoning Province. The LSTM-CAM model stood out for suppressing spurious high-probability signals in Xinjiang, where observed impacts were mild, illustrating how attention mechanisms filter weakly relevant or noisy inputs. In an independent out-of-sample validation using localized frost events from 2012 and 2013 that the models had never seen, the LSTM-CAM architecture achieved the highest AUC values of 0.81 and 0.84 and true positive rates of 0.67 and 0.70, demonstrating stronger cross-year generalization than the tree ensembles when frost events were spatially sparse.

The authors are candid about the framework’s limits. All training samples came from the flowering period, so phenological susceptibility was implicitly controlled by the sampling design rather than modeled explicitly; incorporating observed or simulated flowering dates could sharpen the biological timing of risk. High-quality, spatially continuous frost-damage records remain scarce and concentrated in a few extreme years, constraining the models’ ability to capture interannual variability. Site-based observations also measure air temperature at standard heights, which can diverge substantially from the tissue-level temperatures at which flowers actually freeze, and frost thresholds calibrated for one region may mislead in another. The researchers argue that region-specific thresholds and multi-source long-term datasets are essential next steps.

Even with those caveats, the study delivers a scalable, transparent early-warning tool at a moment when climate change is reshaping frost risk worldwide. Warmer winters advance bud break and flowering, while cold intrusions still arrive, and the resulting collision between sensitive phenological stages and subzero air threatens yields in every major temperate fruit region. By proving that geographic context materially improves frost prediction, and by showing that explainable AI can reveal not just what a model predicts but why, the work offers orchardists and policymakers a defensible basis for targeted frost protection, from wind machines that break up cold-air pooling to siting decisions for new plantings. The next devastating frost may still be unavoidable, but with interpretable machine learning watching the weather and the terrain, it need not be a surprise.

Subject of Research: Explainable machine learning prediction of late-spring frost risks in apple production using meteorological and geospatial features

Article Title: Integrating explainable machine learning models with geospatial features to enhance the prediction of late-spring frost risks in apple production

Article References: Zhou, J., Ru, X., He, Z., Gong, K., Wang, J., Wang, Z., Li, M., Feng, H., Yu, Q., & He, J. (2026). Integrating explainable machine learning models with geospatial features to enhance the prediction of late-spring frost risks in apple production. Artificial Intelligence in Agriculture. https://doi.org/10.1016/j.aiia.2026.08.017

Image Credits: AI Generated

DOI: 10.1016/j.aiia.2026.08.017

Keywords: late-spring frost, apple production, machine learning, explainable AI, SHAP, Random Forest, LSTM, attention mechanism, geospatial features, frost prediction, China agriculture, climate risk