eKeth: A Machine Learning-Based Mobile Platform to Facilitate the Paddy Cultivation Process in Sri Lanka

Author(s):  
J.S.A.N.W. Premachandra ◽  
P.P.N.V. Kumara
2019 ◽  
Vol 1 (1) ◽  
pp. 33-44
Author(s):  
M B Ranathilaka ◽  
I.A.J Imbulana Arachchi

Paddy cultivation is major part in rural agriculture sector in Sri Lanka. Majority of rural sector paddy farmers are small-scale producers. According to available data paddy production sector provides livelihood opportunities for large numbers of rural population, provide rice requirement of the nation, provide inputs to other industrial sector etc.To enhance small-scale farmers living condition as well as paddy production, Sri Lankan government promotes paddy farmers to use more fertilizer for their paddy cultivation activities. Therefore, Sri Lankan government provides subsidized fertilizer to enhance both paddy production and paddy yield per acre. Last few decades paddy production and paddy yield per acre data show continues increasing trend. At the same time government expenditure on fertilizer also becomes heavy burden to national budget. There are arguments for and against to fertilizer subsidy program and its practice. This study attempts to study the effect of fertilizer subsidy on paddy production and living condition of small-scale farmers in Polonnaruwa district in Sri Lanka. The data are used to estimate an econometric model to find the relationship between paddy productivity, fertilizer subsidy, agricultural infrastructure facilities and farmers education level. The data were collected from Bubula and Raja-elagama villages in Higurakgoda divisional secretariat in Polonnaruwa district. Structured questioner was used to collect the data from 150 farmers. The results show that there is significant relationship between paddy production and dependent variables named fertilizer subsidy, agricultural infrastructure facilities and farmers education level. Especially fertilizer subsidy and paddy productivity is significant at 5 per cent level and R2 was 0.68. This result shows that government main objective of fertilizer subsidy that improves paddy productivity has been fulfilled. At the same time, household income from paddy has also increased and it has affected their livelihoods. But poor agricultural infrastructural facilities have mitigated farmers’ income. Research results and some empirical evidence have concluded that it is important to find alternative methods to select suitable and needy farmers who are eligible to get fertilizer subsidy because conducting methods of distributing have made many kinds of effects on the efficiency of resource utilization, equity of income distribution as well as government budget. Agricultural infrastructure facilities are very important for making fertilizer subsidy programs more meaningful and to have a significant effect on enhancing paddy farmers’ living conditions.


2020 ◽  
pp. 016224392092035
Author(s):  
Adam Fish

Drones deployed to monitor endangered species often crash. These crashes teach us that using drones for conservation is a contingent practice ensnaring humans, technologies, and animals. This article advances a crash theory in which pilots, conservation drones, and endangered megafauna are relata, or related actants, that intra-act, cocreating each other and a mutually constituted phenomena. These phenomena are entangled, with either reciprocal dependencies or erosive entrapments. The crashing of conservation drones and endangered species requires an ethics of care, repair, or reworlding. Diffractions, disruptions that expose difference, result from crashes and reveal the precarious manner by which technologies, laws, and discourses bring nature and culture together. To support crash theory, this article presents three ethnographic cases. A drone crash in the United Kingdom near white rhinoceroses while building machine learning training data exhibits the involvement of the electromagnetic spectrum; the threat of crashes in the Pacific Northwest near Puget Sound orcas discloses the impacts of drone laws; and drone crashes in Sri Lanka among Asian elephants presents the problems of technoliberal ideals around programming natural worlds. Throughout the article, a methodology is developed, parallelism, which attends to the material similarities in lateral phenomena.


Author(s):  
G.L.V. Mihiranga ◽  
W.K.M. Weerasooriya ◽  
T.L.P. Palliyaguruge ◽  
P.N.G. Gunasekera ◽  
M.P. Gamage ◽  
...  

2016 ◽  
Vol 10 (2) ◽  
pp. 144-160 ◽  
Author(s):  
PA Chintaka T. Perera ◽  
Thenmoli V. Sundarabarathy ◽  
Thavananthan Sivananthawerl ◽  
Suranga P. Kodithuwakku ◽  
Udeni Edirisinghe

2021 ◽  
Vol 2021 ◽  
pp. 1-14
Author(s):  
Piyal Ekanayake ◽  
Windhya Rankothge ◽  
Rukmal Weliwatta ◽  
Jeevani W. Jayasinghe

This paper presents the development of crop-weather models for the paddy yield in Sri Lanka based on nine weather indices, namely, rainfall, relative humidity (minimum and maximum), temperature (minimum and maximum), wind speed (morning and evening), evaporation, and sunshine hours. The statistics of seven geographical regions, which contribute to about two-thirds of the country’s total paddy production, were used for this study. The significance of the weather indices on the paddy yield was explored by employing Random Forest (RF) and the variable importance of each of them was determined. Pearson’s correlation and Spearman’s correlation were used to identify the behavior of correlation in a positive or negative direction. Further, the pairwise correlation among the weather indices was examined. The results indicate that the minimum relative humidity and the maximum temperature during the paddy cultivation period are the most influential weather indices. Moreover, RF was used to develop a paddy yield prediction model and four more techniques, namely, Power Regression (PR), Multiple Linear Regression (MLR) with stepwise selection, forward (step-up) selection, and backward (step-down) elimination, were used to benchmark the performance of the machine learning technique. Their performances were compared in terms of the Root Mean Squared Error (RMSE), Correlation Coefficient (R), Mean Absolute Error (MAE), and the Mean Absolute Percentage Error (MAPE). As per the results, RF is a reliable and accurate model for the prediction of paddy yield in Sri Lanka, demonstrating a very high R of 0.99 and the least MAPE of 1.4%.


Author(s):  
W. D. M. Wijenayaka ◽  
S. B. Weerakoon ◽  
Farncis Mutua

Abstract Irrigation water management in the paddy cultivation area under the left bank canal of the Kaudulla reservoir (Kaudulla tank) in the North Central Province of Sri Lanka has become a serious issue due to limited water availability and inefficient water distribution infrastructure at present. Insufficient storage capacities of the village tanks in the cultivation area, low rainfall during some months and regulated inflow from the transbasin diversion to Kaudulla tank have had a significant impact on yield in the two cultivation seasons of the year. In this article, modernization of irrigation infrastructure in the command area was investigated for effective utilization of limited available water. The results of the calibrated and validated HEC-HMS model and CROPWAT model were used with WEAP to evaluate the water balance and demand to identify the best investment for improving irrigation water supply to maximize the return. Economic analysis was carried out using the net present values for different modernization options. Accordingly, the construction of a new canal system and augmentation of the capacities of village tanks from the present total capacity of 3.8–20 MCM was found to be the most appropriate option. This intervention will increase the income from yield by 205 million with a payback period of 12 years in the Yala season.


Sign in / Sign up

Export Citation Format

Share Document