This study investigates the impact of packaging materials and cold storage on the postharvest quality and shelf life of jasmine (Jasminum multiflorum) flowers and applies machine learning algorithms to predict shelf life based on key quality indicators-physiological loss in weight (PLW), browning index (BI), and total phenol content. Flowers were stored at 5 degrees C +/- 2 degrees C for 20 days in three packaging types: CFB box with polyethylene (PE) lining, bamboo basket with newspaper lining, and nylon bag. Maximum shelf life was observed in CFB with PE lining (16 days) and minimum in bamboo basket (8 days). Machine learning models-Random Forest (RF), Bayesian Regularized Neural Network (BRNN), and Support Vector Machine (SVM)-were trained using the experimental data. Among them, BRNN achieved the best performance with RMSE = 1.03, MSE = 1.06, and R 2 = 0.97 for shelf-life prediction, outperforming RF (RMSE = 1.96, R 2 = 0.91) and SVM (RMSE = 1.46, R 2 = 0.94). The study demonstrates the potential of integrating physiological data with machine learning models for accurate shelf-life prediction and quality management in floriculture. This study uniquely combines physical experimentation with AI-based prediction, offering a dual contribution of empirical validation and scalable digital forecasting for jasmine flower shelf life.
Background: Pigeonpea [Cajanus cajan (L.) Millsp.] is a vital legume crop in the semiarid tropics of Asia, Eastern Africa and the Caribbean Islands. The availability of healthy, pathogen free seeds plays a pivotal role in achieving an optimal plant population and subsequently influencing yield parameters in pigeonpea. Methods: The laboratory and field experiments were arranged using a completely randomized design and a randomized block design with a factorial concept, involving eight genotypes and three bioagents. Result: Seed mycoflora was 8.2% higher with the standard blotter method (32.65%) than with the water agar method (30.17%). Aspergillus niger (9.77%) and A. flavus (9.97%) were the predominant seed mycoflora species identified across various pigeonpea genotypes. Among the pigeonpea genotypes, BSMR-736 showed the highest performance, with plant height (12.4%), number of primary branches (14.7%), secondary branches (21.6%), number of pods per plant (40.6%), seeds per pod (15.9%), seed yield per plant (22.7%) and seed yield per hectare (30.9%) compared to the mean of the tested genotypes. TS-3R took the minimum days to reach 50% flowering (99.70) and maturity (149.63). The combination of polymer @ 3 ml kg-1 + Trichoderma harzianum and Pseudomonas fluorescens each @ 5 g kg-1 demonstrated positive effects on various growth and yield traits, pods per plant (47.0%), seed yield per plant (14.3%) and seed yield per hectare (6.7%) over the treated mean. The application of bioagents, especially the combination of polymer with seed treatment using T. harzianum and P. fluorescens, exhibited the potential to enhance overall plant performance.
Since, Spodoptera frugiperda introduction occurred in India in 2018, the fall armyworm (Spodoptera frugiperda) has severely threatened maize production, leading to the widespread use of synthetic pesticides. These chemicals negatively affect human health, the environment, and product quality. The results of integration of effective approaches for fall armyworm management in maize ecosystem revealed that emamectin benzoate 5 SG spray @ 0.2 gram/litre at 20 days after spraying (DAS)- chlorantraniliprole 18.5 SC spray @ 0.2 millilitre/litre at 30 DAS spinetoram11.7 SC spray 0.5 millilitre/litre at 45 DAS treatment which was on par with seed treatment with cyantraniliprole 19.8
Paddy is one of the major cereal crops grown under diverse agro-ecological conditions of Karnataka. Productivity of paddy is often limited due to poor nutrient use efficiency and imbalanced fertilizer management under field conditions. A field experiment was conducted at the University of Agricultural Sciences, GKVK, Bengaluru during Kharif-2022 to study the growth and yield performance of paddy as influenced by LCO-fortified biofertilizers and nano nitrogen. The experiment was laid out in a Randomized Complete Block Design with seven treatments replicated thrice. Treatments consisted of different combinations of lipo-chito oligosaccharide (LCO) fortified biofertilizer, nano urea, mycorrhizae, and different levels (100 and 75%) of recommended dose of fertilizers. Yield attributes varied significantly among treatments, and application of 100% RDF + LCO-fortified biofertilizer @ 10 kg ha-1 + foliar spray of nano urea @ 0.2% at 30 and 60 DAT (T4) recorded higher number of productive tillers (589 m-2 ), number of panicles (584 m-2 ), panicle length (22.3 cm), grain weight (3.86 g panicle-1 ), number of grains (176.7 panicle-1 ) at harvest compared to only application of 100 % Rec. NPK as per PoP (T1). Higher grain yield (7056 kg ha-1 ), straw yield (7556 kg ha-1 ), and harvest index (0.48) were recorded with this treatment, while lower values (grain yield 5224 kg ha-1 , straw yield 6364 kg ha-1 , and harvest index 0.45) were obtained in T1. Similarly, nutrient uptake of nitrogen, phosphorus, and potassium (95.99, 36.54, and 83.25 kg ha-1 , respectively), gross returns (Rs. 1,69,144 ha-1 ), net returns (Rs. 1,12,447 ha-1 ), and B:C ratio (2.98) were higher with 100% RDF + LCO-fortified biofertilizer + nano urea treatment compared to other treatments.
Assessing soil fertility and spatial variability is essential for site-specific fertilizer recommendations in heterogeneous soils. This study evaluated the fertility status of Bankanahalli micro-watershed, Mandya taluk in the southern dry-zone of Karnataka with an annual rainfall of 633.91 mm and LGP of 120 days. A total of 45 grid-based (320 × 320 m) surface soil samples were analyzed for key fertility parameters. Results showed that available nitrogen, phosphorus and potassium ranged from 119.17 to 567.62, 16.42–84.17 and 24.24–236.88 kg ha− 1, respectively. Soils were low in organic carbon, slightly to moderately alkaline (pH 6.32–8.64) and non-saline (EC 0.01–0.46 dS m− 1). Spatial variability of nutrients was quantified using ordinary kriging in ArcGIS 10.5. Thematic maps were prepared using best-fit semivariogram models with lower RMSE values. The study’s key novelty was recalibrating conventional low, medium, high (L-M-H) fertility ratings to a five-tier system: very low, low, medium, high, and very high (VL-L-M-H-VH), enabling finer nutrient variability capture. Raster maps of fertility variability were reclassified and overlaid to generate combination fertility maps for both systems, followed by site-specific fertilizer recommendations. This classification revealed greater nitrogen and potassium needs, enhancing precision in identifying nutrient-deficient areas and improving nutrient use efficiency and productivity.
