Soil-Plant Relationships

Regression problems provide some of the most challenging research opportunities in the area of machine learning, and more broadly intelligent systems, where the predictions of some target variables are critical to a specific application. Rainfall is a prime example, as it exhibits unique characteristics of high volatility and chaotic patterns that do not exist in other time series data. This work’s main impact is to show the benefit machine learning algorithms, and more broadly intelligent systems have over the current state-of-the-art techniques for rainfall prediction within rainfall derivatives. We apply and compare the predictive performance of the current state-of-the-art (Markov chain extended with rainfall prediction) and six other popular machine learning algorithms, namely: Genetic Programming, Support Vector Regression, Radial Basis Neural Networks, M5 Rules, M5 Model trees, and k-Nearest Neighbours. To assist in the extensive evaluation, we run tests using the rainfall time series across data sets for 42 cities, with very diverse climatic features. This thorough examination shows that the machine learning methods are able to outperform the current state-of-the-art. Another contribution of this work is to detect correlations between different climates and predictive accuracy. Thus, these results show the positive effect that machine learning-based intelligent systems have for predicting rainfall based on predictive accuracy and with minimal correlations existing across climates.

An extensive evaluation of seven machine learning methods for rainfall prediction in weather derivatives

Prediction of rainfall is one of the major concerns in the domain of meteorology. Several techniques have been formerly proposed to predict rainfall based on statistical analysis, machine learning and deep learning techniques. Prediction of time series data in meteorology can assist in decision-making processes carried out by organizations responsible for the prevention of disasters. This paper presents Intensified Long Short-Term Memory (Intensified LSTM) based Recurrent Neural Network (RNN) to predict rainfall. The neural network is trained and tested using a standard dataset of rainfall. The trained network will produce predicted attribute of rainfall. The parameters considered for the evaluation of the performance and the efficiency of the proposed rainfall prediction model are Root Mean Square Error (RMSE), accuracy, number of epochs, loss, and learning rate of the network. The results obtained are compared with Holt–Winters, Extreme Learning Machine (ELM), Autoregressive Integrated Moving Average (ARIMA), Recurrent Neural Network and Long Short-Term Memory models in order to exemplify the improvement in the ability to predict rainfall.

Prediction of Rainfall Using Intensified LSTM Based Recurrent Neural Network with Weighted Linear Units

Development of advanced artificial intelligence models for daily rainfall prediction

Rainfall prediction targets the determination of rainfall conditions over a specific location. It is considered vital for the agricultural industry and other industries. In this paper, we propose a new forecasting method that uses a deep convolutional neural network (CNN) to predict monthly rainfall for a selected location in eastern Australia. To our knowledge, this is the first time applying a deep CNN in predicting monthly rainfall. The proposed approach was compared against the Australian Community Climate and Earth-System Simulator-Seasonal Prediction System (ACCESS), which is a forecasting model released by the Bureau of Meteorology. In addition, the CNN was compared against a conventional multi-layered perceptron (MLP). The better mean absolute error, root mean square error (RMSE), Pearson correlation (r), and Nash Suttcliff coefficient of efficiency values were obtained with the proposed CNN. A difference of 37.006 mm was obtained in terms of RMSE compared with ACCESS and 15.941 compared with conventional MLP. Further investigation revealed that the CNN was generally performing better in months with higher annual averages, while ACCESS was performing better in months with low annual averages. The generated output is promising and can be widely extended in this type of applications.

Monthly Rainfall Forecasting Using One-Dimensional Deep Convolutional Neural Network

Rainfall Monthly Prediction Based on Artificial Neural Network: A Case Study in Tenggarong Station, East Kalimantan - Indonesia

This study aimed to (1) determine the effect of each organic fertilizer dosage (a) the growth variables of Trembesi seedlings and (b) the quality of planting media after 120 days planted Trembesi Seedlings. This study also aimed to (2) obtain the optimum dose of organic fertilizer to be applied to the implementation of post-mining land reclamation and revegetation within the Forest Cultivation Zone. This research used various manure: Control without fertilizer; NPK synthetic fertilizer control; chicken manure, cow manure, and organic litter compost. Each of the organic fertilizer was given at doses of 125, 250, and 375 g/polybag. The test plants used were Trembesi seedlings (Samanea saman) at 4 months of age.The experimental design was prepared using Randomized Block Design (RAK) with 5 replications in each test plant group. Data analysis was completed with Fisher LSD Test and Duncan Multiple Range Test (DMRT) as well as regression analysis.The treatment of organic fertilizer dosage showed significant in all variables of growth of trembesi seedlings, except on average of Trembesi seedlings height at 90 days after planting (DAP) and on average stem diameter of Trembesi seed of 30, 60, 90, 120 DAP. Effect of organic fertilizer dosage to planting medium after 120 days planted Trembesi seedling. All variations of fertilization dose increase the pH value, organic C, N-total, C/N ratio, available P, available K, Ca++, Mg++, Na+, K and cation exchange rate (CEC). Treatment dose of 375g/polybag of chicken manure was the best treatment dose with the highest number of twigs on Trembesi seedlings at the age of 30 DAP (21.00 twigs), 60 DAP (36.40 twigs), 90 DAP (63.60 twigs), 120 DAP (106.60 twigs), The Longest length of twig was found on Trembesi seedlings with age of 30 DAP (17.95 cm), 60 DAP(21.61 cm), 90 DAP (28.49 cm), 120 DAP (32.11 cm), longest root length and heaviest biomass weight of Trembesi seedling wasfor the age of 120 DAP, which were 58.80 cm and 487.22 g, respectively.

Organic Fertilizers Improves Trembesi (Samanea Saman) Seedling Growth, A Case Study Of The Implementation Of Post-Mining Land Reclamation And Revegetation Within The Forest Cultivation Zone

This research aimed to identify the participation level of communities in the management program of Sorong Nature Tourism Park (NTP) and to provide alternative recommendations that can be used to support the success of the management program based on community participation. The results of the research showed that community participation in the management of Sorong NTP had the highest values in the household group (15 respondents or 40,54%) and the lowest was group leader (1 respondent or 2,70%), similar with the intensity of community participation. Community participation in Sorong NTP includes group leaders, interest group , head of household, women/ housewives and youth . The participation level was categorized into very inactive and inactive, influenced by community participation function which generally occurred in the form of implementing activity and intensity of participation of society element in the form of p rovid ing consultation and information. Management efforts include seeking legal aspects of the area to be the basis of management programs , seeking the payment of customary rights to ensure the existence of claims-related areas of the community , involving communities in planning, maintenance, management, decision-making, initiating action and control programs , and increasing the frequency of socialization and counseling to provide insight into the community about the economic means and the ecological meaning of the results of management program.

/pdf/community-participation-in-the-management-of-sorong-nature-377jg8dbuh.pdf

Community Participation in the Management of Sorong Nature Tourism Park, Sorong City

Land cover is a biophysical cover that maintains land conditions in water balance. The purpose of this research is to know the condition of land cover, water catchment, groundwater aquifer and correlation. This research begins by collecting data on land cover, soil type, rainfall, slopes and groundwaterinformation. Field activities include observation and data collection of land cover, geological conditions, community wells and geoelectric sounding. Land cover data is classified according to circumstances and conditions. Geoelectric sounding data was analyzed with IP2WIN software, interpretation of lithologic variation of rocks and depth based on resistivity value. Plot the position of each lithology sounding with Surfer software obtained kontour rock field boundary and 3D model of the aquifer position.The results showed that the land cover consisted of vegetated areas: forests 272,21 Ha (40,32%) and agricultural land 183,36 Ha (27,16%) non-vegetation area: 98,80 Ha (14,64%) constructed land, , Open land 116.33 Ha (17.23%) and water body 4.35 Ha (0.64%) The condition of land cover in this water catchment area has decreased 68,38 Ha (10,14%) from the previous condition 340,59 Ha (50,46%) to 272,21 Ha (40,32%). Referring to Permenhut RI No. 32 in 2009, total score catchment area 33, including the somewhat critical condition. Groundwater aquifers based on 3D sounding geolistrik modeling consist of a free aquifer for shallow groundwater depth of water level between (2-30) m with thickness ± (2-65) m and a distorted aquifer for groundwaterin depth of water between 75-150 m With thickness ± (75125) m, depth of community well ± (10-45) m. The transfer of land into open pit mines resulted in the destruction of the balance and water system, the decreasing / decreasing the discharge of the well water of the community drill, the failure and the lack of new water discharge of the new wells, the loss of groundwaterin several dug wells, landslides and mud floods on the farmland

/pdf/study-of-land-cover-and-condition-catchment-area-groundwater-1s5j8z1zf0.pdf

Study Of Land Cover And Condition Catchment Area Groundwater Aquifer In Tanah Merah North Samarinda District Using Resistivity Geoelectric Sounding

This research aimed to determine the degree of participation of local communities in the management program of Gunung Meja natural recreation park and to provide alternative recomendations for the management based on community participation. Community participation in the management of the park was found to be the highest in the family group (46.15%), and the lowest in the leader group (5.13%). The same case was also found in the intensity of community participation. The participation of community includes leaders, interested groups, household heads, housewives and youth which was categorised as very inactive. This inactive result was influenced by community participation function which was in general only participating in activity implemention,information sharing and consultation. The management efforts were permit of natural tourism utilization and natural resources tourism infrastructure utilization, which can be used as the basis of the management program.

/pdf/the-form-and-intensity-of-community-participation-in-4l51w3ebjx.pdf

Sumaryono

Papers

Rainfall Monthly Prediction Based on Artificial Neural Network: A Case Study in Tenggarong Station, East Kalimantan - Indonesia

Organic Fertilizers Improves Trembesi (Samanea Saman) Seedling Growth, A Case Study Of The Implementation Of Post-Mining Land Reclamation And Revegetation Within The Forest Cultivation Zone

Community Participation in the Management of Sorong Nature Tourism Park, Sorong City

Study Of Land Cover And Condition Catchment Area Groundwater Aquifer In Tanah Merah North Samarinda District Using Resistivity Geoelectric Sounding

The Form and Intensity of Community Participation in Conservation Management Program at Papua Barat Province