Deep Learning Models to Determine Nutrient Concentration in Hydroponically Grown Lettuce Cultivars (Lactuca sativa L.)

Deep learning (DL) and computer vision applications in precision agriculture have great potential to identify and classify plant and vegetation species. This study presents the applicability of DL modeling with computer vision techniques to analyze the nutrient levels of hydroponically grown four lettuce cultivars (Lactuca sativa L.), namely Black Seed, Flandria, Rex, and Tacitus. Four different nutrient concentrations (0, 50, 200, 300 ppm nitrogen solutions) were prepared and utilized to grow these lettuce cultivars in the greenhouse. RGB images of lettuce leaves were captured. The results showed that the developed DL’s visual geometry group 16 (VGG16) and VGG19 architectures identified the nutrient levels of lettuces with 87.5 to 100% accuracy for four lettuce cultivars, respectively. Convolution neural network models were also implemented to identify the nutrient levels of the studied lettuces for comparison purposes. The developed modeling techniques can be applied not only to collect real-time nutrient data from other lettuce type cultivars grown in greenhouses but also in fields. Moreover, these modeling approaches can be applied for remote sensing purposes to various lettuce crops. To the best knowledge of the authors, this is a novel study applying the DL technique to determine the nutrient concentrations in lettuce cultivars.

Dose-response models to guide site-specific nutrient management and lessons for fertiliser trial design in sub-Saharan Africa

Summary Optimisation of fertiliser use and site-specific nutrient management are increasingly becoming critical because of the growing need to balance agricultural productivity with the growing demand for food and environmental concerns. Trials to determine responses of crops to fertilisers have been widely conducted in sub-Saharan Africa (SSA) with increasing emphasis on the development of economically optimum rates (EORs). Computation of EORs depends on accurate estimation of both the optimum nutrient rate and the agronomic maximum yield response; however, estimation of nutrient-response parameters and EORs is beset by a number of problems. Therefore, the objectives of this paper were to (1) point out common problems in the development and use of nutrient dose-response models and (2) provide corrective measures to facilitate future trial design and data analysis. This review outlines the underlying assumptions, strengths and limitations of the various response functions in order to facilitate informed choices by practitioners. Using specific examples, it also shows that (1) the commonly used trial designs do not allow examination of interactions between two or more nutrients and (2) trial designs with ≤5 nutrient levels and wide spacing between the levels result in large uncertainty in dose-response parameters. The key recommendations emerging from the review are as follows: (1) factorial designs and response surface models should be used more widely to address interactions between nutrients; (2) a minimum of six carefully spaced nutrient levels should be used to correctly estimate dose-response parameters; and (3) when locating field trials, Reference Soil Groups and cropping history should be carefully considered to produce site-specific EORs.

Yield and Nutrient Uptake of Pigeonpea [Cajanus cajan (L.)] as Influenced by Tillage, Nutrient Levels and Foliar Sprays

A field investigation was conducted during two consecutive kharif seasons of 2019-20 and 2020-21 to study the effect of tillage, nutrient levels and foliar sprays on yield and nutrient uptake of redgram on sandy loam soil which was low in available nitrogen, medium in available phosphorus and available potassium. The research was conducted in a split-split plot design, consisting of three tillage practices in main plots, three nutrient levels in sub-plots and three foliar sprays in sub-sub plots. Higher seed yield and nutrient uptake of redgram was recorded with vertical tillage with subsoiler upto 60 cm deep at 1 m interval with application of 125 % RDF and with foliar application of KNO3 1 % twice with 15 days interval at 50 per cent flowering stage.

Fire impacts tropical communities of soil fungi through changes to plant community composition, litter and soil chemistry

Fire has been predicted to be more severe and frequent in forests of the Australian Monsoon Tropics over the coming decades. The way in which groups of ecologically important soil fungi respond to disturbance caused by fire has not been studied in tropical forest ecosystems. Ectomycorrhizal (EM) fungi are important tree symbionts and saprotrophic fungi drive soil nutrient cycles. We analysed both publicly-available environmental DNA sequence data as well as soil chemistry data to test a hypothesis that fire events (1970 - 2017) in a contiguous tropical forest have altered the composition and diversity of EM and saprotrophic soil fungi. We tested this hypothesis by measuring community-level taxonomic composition, fungal diversity, species richness and evenness. We determined whether changes in fungal communities were associated with fire-altered soil chemical/physical properties, vegetation types, or the direct effect of fire. Soil fungi differed in abundance and community phylogenetic structure between forest sites that had experienced fire, and those sites dominated by unburned forest. Communities of EM fungi were structurally altered by fire at shallow soil horizons, as well as by vegetational changes between burned and unburned sites at deeper soil horizons. In contrast, fires influenced community composition of saprotrophic fungi by changing soil nutrient levels and altering litter composition. Pyrophilic, truffle-like EM fungi that rely on mycophagous mammals for dispersal were abundant at recently burned sites. We conclude that fire impacts EM fungi primarily by changing plant communities, whereas fire impacts saprotrophic fungi by reducing soil nutrient levels and altering litter composition.

Production Potential of Allelopathic Rice, Cymbopogon, Desmodium, Mucuna and Maize

Allelochemicals regulate the productivity of crop ecosystems. A screen house experiment was conducted (2016) at the National Crops Resources Research Institute, Namulonge, Uganda to determine the effects of NERICA 1 rice (an interspecific hybrid between Oryza sativa and O. glaberrima species), Cymbopogon nardus (C), Desmodium uncinatum (D), Mucuna pruriens (Mc) and LONGE 6H, Zea mays (Mz) on crop relative growth rates (RGR), nitrogen (N), phosphorus (P) and potassium (K) nutrient levels. One field study was conducted on a farm (2017) to establish the allelopathic interactive effects of RCDMcMz on Striga hermonthica (a parasitic weed), crop competition and productivity. Data was collected on striga, RMz growth, nutrient levels and yield. Potted rice reduced (30%-47%) in root length but Mz leaf length increased (31% & 15%) with Mc & D. RMc reduced (73%) striga and increased rice RGR (14-42 days). RD similarly reduced (67%) striga. RC increased (96%, 44% & 73%) rice NPK uptake, RGR (14-42 days), reduced (57%) striga and increased (1.56) the combined land equivalent ratio (CLER) and rice grain yields. RMz reduced (16%, 38% & 38%) rice NPK reserves, RGR (14-42 days), CLER (1.0), grain yields and increased (36%) striga. RD recorded higher CLER (1.56). MzMc reduced (15% & 27%) maize P uptake and NP uptake increased (42% & 9.3%) under MzC & MzD (73% & 29%). RMc increased rice RGR (14-42 days). Maize RGR (14-28 days) increased under MzD, MzMc & MzC and reduced (28-42 days) under MzD, RC & MzMc.. The ecosystems’ productivity was attributed to allelopathy.