Thumbnail Image

Theses

Browse

2020 - 20212
Reset filters
Author: Neha × End date: 2021 × Start date: 2020 × Type: Thesis ×
Reset filters

Search Results

Now showing 1 - 2 of 2
  • Thumbnail Image
    ThesisItemOpen Access
    Use of drone in disease identification from leaves by deep learning through YOLO v3 and CNN architecture
    (G.B. Pant University of Agriculture and Technology, Pantnagar - 263145 (Uttarakhand), 2021-02) Neha; Singh, Rajeev
    In recent years Machine Learning and Deep Learning have played a crucial role in the field of agriculture. There are many methods that are adopted in farming so that the yield and production increases. Smart agriculture is itself growing and developing. In automated farming, smart agriculture helps to collect data from the field and then analyze it so that the farmer can make precise decisions to grow high-quality crops. For better agricultural productivity and food management, an agriculture monitoring system is needed. Precision agriculture is also used as new technology for the decision making process. In this work, we have used drone for collecting data in real time from the field. ML algorithm are then used to take optimal decisions which helps in cutting the cost of procedure. Drone systems are also used reliably for operations like UREA spraying wherein involvement of the sensors enables a reliable safe operation with good satisfaction of customer. However, this field is open for improvements majorly in decision support system which helps in converting large amount of data into useful recommendations. Deep learning is a subset of machine learning. It can be used for precision farming, identification of diseases, classification of images etc. This research deals with identification of wheat plant leaf diseases by accessing the leaf morphology of crops by means of drone photography and further analysis of captured images by computer means using YOLO V3 and CNN architecture.
  • Thumbnail Image
    ThesisItemOpen Access
    Performance of Rhizobium and PGPR inoculation in mungbean on productivity and soil properties in mungbean-wheat sequence
    (G.B. Pant University of Agriculture and Technology, Pantnagar - 263145 (Uttarakhand), 2020-08) Neha; Ramesh Chandra
    A field experiment was conducted to study the performance of Rhizobium and PGPR inoculation in mungbean on productivity and soil properties in mungbean-wheat sequence during 2017-18 and 2018-19. Laboratory study was carried out in the Department of Soil Science and the field experiment at Norman E. Borlaug Crop Research Centre of G.B.P.U.A&T, Pantnagar. The five treatments in mungbean consisting of inoculation with Rhizobium and PGPR, alone and in combination, N as RDF and an uninoculated control were randomized in main plots and three N levels (50, 75 and 100% of RDF) in succeeding wheat in sub plots in three replications. The soil was Sandy loam of neutral pH and low in available N, high in available P and medium in available K. The test crop variety of mungbean was Pant mung-5 and wheat PBW-550. Inoculation of different biofertilizer treatments in mungbean and N as RDF increased the mean nodule number, nodule dry weight and plant dry weight of both the years significantly over the uninoculated control. These treatments also significantly increased the leaf chlorophyll content of mungbean ranging from 1.9 to 11.3% at 60 DAS over the uninoculated control during 2018-19. Different treatments in mungbean recorded significantly higher mean grain yield from 2.5 to 11.7% and numerically more straw yield from 3.7 to 12.1% over the uninoculated control. Inoculation also increased the N and P content and its uptake by grain and straw in comparison to the uninoculated control. Mineral N and available N, P, K in soil at harvesting due to different treatments was 3.5 to 25.8%, 3.5 to 18.8%, 9.4 to 57.2% and 2.9 to 18.7% significantly more over the uninoculated control. Different treatments in mungbean also significantly increased the organic C, microbial biomass C, activities of enzymes dehydrogenase, acid and alkaline phosphomonoesterases and respiration rate in soil. Irrespective of N levels, the different treatments in preceding mungbean significantly increased the mean plant dry weight and plant height of wheat of both the years over the uninoculated control at different intervals. The effect of different treatments in preceding mungbean showed the numerical increases in mean grain of 3.1 to 9.7% and straw yield of 2.2 to 9.4% of succeeding wheat over the uninoculated control. Different inoculation treatments also influenced the various yield attributes of wheat viz. effective tillers, mean spike length, grain weight per spike significantly and total tillers, number of spikelets per spike and thousand grain weight numerically. These treatments also significantly increased N, P and K uptake by wheat grain and straw. The treatments in mungbean significantly affected the mineral, ammonical and nitrate N in soil at different intervals. All the inoculation treatments applied in mungbean also recorded higher organic C and available N, P and K in soil at different intervals. A significant variation in mean microbial biomass C and activities of dehydrogenase and acid and alkaline phosphomonoesterases in soil were also noticed at different intervals suggesting their residual impact on soil health. Increasing levels of N significantly increased the wheat grain and straw yields, mineral, ammonical and nitrate N, available N, P and K, microbial biomass C and activities of dehydrogenase and acid and alkaline phosphomonoesterases in soil at different intervals. The maximum net returns of Rs.1,46,071 ha-1 and B:C ratio of 2.74 were noted with combined inoculation of Rhizobium + PGPR. However, among the N levels, the highest net returns of Rs.1,48,603 ha-1 and the B:C ratio of 2.75 was obtained with 100% fertilizer N under mungbean-wheat sequence.