No abstract

Symptoms of nutrient deficiencies in rice plants often appear on the leaves. The leaf color and shape, therefore, can be used to diagnose nutrient deficiencies in rice. Image classification is an efficient and fast approach for this diagnosis task. Deep convolutional neural networks (DCNNs) have been proven to be effective in image classification, but their use to identify nutrient deficiencies in rice has received little attention. In the present study, we explore the accuracy of different DCNNs for diagnosis of nutrient deficiencies in rice. A total of 1818 photographs of plant leaves were obtained via hydroponic experiments to cover full nutrition and 10 classes of nutrient deficiencies. The photographs were divided into training, validation, and test sets in a 3 : 1 : 1 ratio. Fine-tuning was performed to evaluate four state-of-the-art DCNNs: Inception-v3, ResNet with 50 layers, NasNet-Large, and DenseNet with 121 layers. All the DCNNs obtained validation and test accuracies of over 90%, with DenseNet121 performing best (validation accuracy = 98.62 ± 0.57%; test accuracy = 97.44 ± 0.57%). The performance of the DCNNs was validated by comparison to color feature with support vector machine and histogram of oriented gradient with support vector machine. This study demonstrates that DCNNs provide an effective approach to diagnose nutrient deficiencies in rice.

Water, energy, and biodiversity are essential components for building a sustainable food system in a developing country like Nepal. Green Revolution technologies and the package of practices largely ignored the role of ecosystem services, leaving a large population of small farmers’ food- and nutrition-insecure. Biodiversity, especially, agrobiodiversity is in decline and this vital cross-cutting element is less discussed and interlinked in nexus literature. The interlinking food system with water–energy–biodiversity nexus, therefore, is essential to achieve a resilient food system. It ensures the vital structures and functions of the ecosystem on which it is dependent are well protected in the face of increasing socio-economic and climatic stress. This paper reviews the food system of Nepal through the lens of the food–water–energy–biodiversity (FWEB) nexus to develop a more robust food system framework. From this approach, food system foresight can benefit from different nature-based solutions such as agro-ecosystem-based adaptation and mitigation and climate-resilient agro-ecological production system. We found that the FWEB nexus-based approach is more relevant in the context of Nepal where food and nutrition insecurity prevails among almost half of the population. Improvement in the food system requires the building of synergy and complementary among the components of FWEB nexus. Hence, we proposed a modified framework of food system foresight for developing resilience in a food system, which can be achieved with an integrated and resilient nexus that gives more emphasis to agro-ecological system-based solutions to make the food system more climate resilient. This framework can be useful in addressing the Sustainable Development Goals (SDGs) numbers 1, 2, 3, 6, 13, and 15 and can also be used as a tool for food system planning based on a broader nexus.

Wheat is the third most important cereal crop in Nepal after rice and maize both in area and production, but its productivity of 2.3 tonne ha À1 is very less compared to other developed countries (6 tonne ha À1 for Switzerland and China) in the world. The main cause of low wheat yield in Nepal is the improper and inadequate use of fertilizer devoid of site specific nutrient management practices. Therefore, a farmers' field experiment was conducted during November 2015 to April 2016 to rectify the best fertilizer management options at two sites of Damak and Gauradaha in Jhapa district in eastern-Terai of Nepal using Nutrient Expert ® -Wheat model. The research was accomplished in Randomized Complete Block Design with 2 treatments and 20 replications, considering farmers' field as replication. Two treatments included in the experimentation were NE ® (Nutrient Expert Recommendation) and FFP (Farmer's Fertilizer Practices). The statistical result revealed the highly significant difference in terms of number of effective tiller m À2 , plant height, filled grain per spike, spike length, grain, straw and biological yields and harvest index. The highest yield (4.71 tonne ha À1 ) was obtained from NE field than FFP (2.99 tonne ha À1 ). On an average, NE based practices produced 58 % higher yield in comparison to FFP. NE based treatment produced significantly higher biomass yield, yield attributes and cost-benefit ratio than FFP treatments. Field experiment validation confirmed that the Nutrient Expert ® Wheat model could be used as the most adoptable and practical precision decision support system tool to make a more authentic fertilizer recommendation in eastern-Terai of Nepal.