scholarly journals Seasonal forecasting of hydrological drought in the Limpopo basin: A comparison of statistical methods.

2016 ◽  
Author(s):  
Mathias Seibert ◽  
Bruno Merz ◽  
Heiko Apel
Keyword(s):  
Neural Networks ◽  
Random Forest ◽  
Early Warning ◽  
Linear Models ◽  
Regression Trees ◽  
Forecast Skill ◽  
Sea Surface ◽  
Coefficient Of Determination ◽  
Operating Characteristics ◽  
Random Forest Regression

Abstract. The Limpopo basin in southern Africa is prone to droughts, which affect the livelihoods of millions of people in South Africa, Botswana, Zimbabwe, and Mozambique. Seasonal drought early warning is thus vital for the whole region. In this study, the predictability of hydrological droughts during the main runoff period from December to May is assessed with statistical approaches. Three methods (Multiple Linear Models, Artifical Neural Networks, Random Forest Regression Trees) are compared in terms of their ability to forecast streamflow with up to 12 months lead time. The following four main findings result from the study. 1) There are stations in the basin at which standardised streamflow is predictable with lead times up to 12 months. The results show high interstation differences of forecast skill but reach a coefficient of determination as high as 0.73 (cross validated). 2) A large range of potential predictors is considered in this study, comprising well established climate indices, customised teleconnection indices derived from sea surface temperatures, and antecedent streamflow as proxy of catchment conditions. El-Niño and customised indices, representing sea surface temperature in the Atlantic and Indian Ocean, prove to be important teleconnection predictors for the region. Antecedent streamflow is a strong predictor in small catchments (with median 42 % explained variance), whereas teleconnections exert a stronger influence in large catchments. 3) Multiple linear models show the best forecast skill in this study and the greatest robustness compared to artificial neural networks and Random Forest regression trees, despite their capabilities to represent non-linear relationships. 4) Employed in early warning the models can be used to forecast a specific drought level. Even if the coefficient of determination is low, the forecast models have a skill better than a climatological forecast, which is shown by analysis of receiver operating characteristics (ROC). Seasonal statistical forecasts in the Limpopo show promising results, and thus it is recommended to employ them complementary to existing forecasts in order to strengthen preparedness for droughts.

scholarly journals Seasonal forecasting of hydrological drought in the Limpopo Basin: a comparison of statistical methods

2017 ◽  
Vol 21 (3) ◽  
pp. 1611-1629 ◽  
Author(s):  
Mathias Seibert ◽  
Bruno Merz ◽  
Heiko Apel
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Random Forest ◽  
Early Warning ◽  
Linear Models ◽  
Regression Trees ◽  
Forecast Skill ◽  
Sea Surface ◽  
Coefficient Of Determination ◽  
Random Forest Regression

Abstract. The Limpopo Basin in southern Africa is prone to droughts which affect the livelihood of millions of people in South Africa, Botswana, Zimbabwe and Mozambique. Seasonal drought early warning is thus vital for the whole region. In this study, the predictability of hydrological droughts during the main runoff period from December to May is assessed using statistical approaches. Three methods (multiple linear models, artificial neural networks, random forest regression trees) are compared in terms of their ability to forecast streamflow with up to 12 months of lead time. The following four main findings result from the study. 1. There are stations in the basin at which standardised streamflow is predictable with lead times up to 12 months. The results show high inter-station differences of forecast skill but reach a coefficient of determination as high as 0.73 (cross validated). 2. A large range of potential predictors is considered in this study, comprising well-established climate indices, customised teleconnection indices derived from sea surface temperatures and antecedent streamflow as a proxy of catchment conditions. El Niño and customised indices, representing sea surface temperature in the Atlantic and Indian oceans, prove to be important teleconnection predictors for the region. Antecedent streamflow is a strong predictor in small catchments (with median 42 % explained variance), whereas teleconnections exert a stronger influence in large catchments. 3. Multiple linear models show the best forecast skill in this study and the greatest robustness compared to artificial neural networks and random forest regression trees, despite their capabilities to represent nonlinear relationships. 4. Employed in early warning, the models can be used to forecast a specific drought level. Even if the coefficient of determination is low, the forecast models have a skill better than a climatological forecast, which is shown by analysis of receiver operating characteristics (ROCs). Seasonal statistical forecasts in the Limpopo show promising results, and thus it is recommended to employ them as complementary to existing forecasts in order to strengthen preparedness for droughts.

scholarly journals Bus Travel Time Prediction: A Comparative Study of Linear and Non-Linear Machine Learning Models

2022 ◽  
Vol 2161 (1) ◽  
pp. 012053
Author(s):  
B P Ashwini ◽  
R Sumathi ◽  
H S Sudhira
Keyword(s):  
Random Forest ◽  
Travel Time ◽  
Linear Models ◽  
Public Transit ◽  
Regression Trees ◽  
Support Vector ◽  
Learning Models ◽  
Random Forest Regression ◽  
The Public ◽  
Non Linear

Abstract Congested roads are a global problem, and increased usage of private vehicles is one of the main reasons for congestion. Public transit modes of travel are a sustainable and eco-friendly alternative for private vehicle usage, but attracting commuters towards public transit mode is a mammoth task. Commuters expect the public transit service to be reliable, and to provide a reliable service it is necessary to fine-tune the transit operations and provide well-timed necessary information to commuters. In this context, the public transit travel time is predicted in Tumakuru, a tier-2 city of Karnataka, India. As this is one of the initial studies in the city, the performance comparison of eight Machines Learning models including four linear namely, Linear Regression, Ridge Regression, Least Absolute Shrinkage and Selection Operator Regression, and Support Vector Regression; and four non-linear models namely, k-Nearest Neighbors, Regression Trees, Random Forest Regression, and Gradient Boosting Regression Trees is conducted to identify a suitable model for travel time predictions. The data logs of one month (November 2020) of the Tumakuru city service, provided by Tumakuru Smart City Limited are used for the study. The time-of-the-day (trip start time), day-of-the-week, and direction of travel are used for the prediction. Travel time for both upstream and downstream are predicted, and the results are evaluated based on the performance metrics. The results suggest that the performance of non-linear models is superior to linear models for predicting travel times, and Random Forest Regression was found to be a better model as compared to other models.

scholarly journals Improving Australian Rainfall Prediction Using Sea Surface Salinity

2021 ◽  
pp. 1-56
Author(s):  
Saurabh Rathore ◽  
Nathaniel L. Bindoff ◽  
Caroline C. Ummenhofer ◽  
Helen E. Phillips ◽  
Ming Feng ◽  
...  
Keyword(s):  
Soil Moisture ◽  
Random Forest ◽  
Indian Ocean ◽  
Indian Ocean Dipole ◽  
Sea Surface ◽  
Sea Surface Salinity ◽  
Surface Salinity ◽  
Random Forest Regression ◽  
Dry Conditions ◽  
Australian Rainfall

AbstractThis study uses sea surface salinity (SSS) as an additional precursor for improving the prediction of summer (December-February, DJF) rainfall over northeastern Australia. From a singular value decomposition between SSS of prior seasons and DJF rainfall, we note that SSS of the Indo-Pacific warm pool region [SSSP (150°E-165°W and 10°S-10°N), and SSSI (50°E-95°E and 10°S-10°N)] co-varies with Australian rainfall, particularly in the northeast region. Composite analysis based on high (low) SSS events in SSSP and SSSI region is performed to understand the physical links between the SSS and the atmospheric 31 moisture originating from the regions of anomalously high (low) SSS and precipitation over Australia. The composites show the signature of co-occurring La Niña and negative Indian Ocean dipole (co-occurring El Niño and positive Indian Ocean dipole) with anomalously wet (dry) conditions over Australia. During the high (low) SSS events of SSSP and SSSI regions, the convergence (divergence) of incoming moisture flux results in anomalously wet (dry) conditions over Australia with a positive (negative) soil moisture anomaly. We show from the random forest regression analysis that the local soil moisture, El Niño Southern Oscillation (ENSO) and SSSP are the most important precursors for the northeast Australian rainfall whereas, for the Brisbane region ENSO, SSSP and Indian Ocean Dipole (IOD) are the most important. The prediction of Australian rainfall using random forest regression shows an improvement by including SSS from the prior season. This evidence suggests that sustained observations of SSS can improve the monitoring of the Australian regional hydrological cycle.

scholarly journals Application of Machine Learning Techniques to an Agent-Based Model of Pantoea

2021 ◽  
Vol 12 ◽  
Author(s):  
Serena H. Chen ◽  
Pablo Londoño-Larrea ◽  
Andrew Stephen McGough ◽  
Amber N. Bible ◽  
Chathika Gunaratne ◽  
...  
Keyword(s):  
Neural Network ◽  
Random Forest ◽  
Dynamic System ◽  
Machine Learning Techniques ◽  
Coefficient Of Determination ◽  
Computational Time ◽  
Complex Dynamic ◽  
Random Forest Regression ◽  
Complex Dynamic System ◽  
Agent Based

Agent-based modeling (ABM) is a powerful simulation technique which describes a complex dynamic system based on its interacting constituent entities. While the flexibility of ABM enables broad application, the complexity of real-world models demands intensive computing resources and computational time; however, a metamodel may be constructed to gain insight at less computational expense. Here, we developed a model in NetLogo to describe the growth of a microbial population consisting of Pantoea. We applied 13 parameters that defined the model and actively changed seven of the parameters to modulate the evolution of the population curve in response to these changes. We efficiently performed more than 3,000 simulations using a Python wrapper, NL4Py. Upon evaluation of the correlation between the active parameters and outputs by random forest regression, we found that the parameters which define the depth of medium and glucose concentration affect the population curves significantly. Subsequently, we constructed a metamodel, a dense neural network, to predict the simulation outputs from the active parameters and found that it achieves high prediction accuracy, reaching an R2 coefficient of determination value up to 0.92. Our approach of using a combination of ABM with random forest regression and neural network reduces the number of required ABM simulations. The simplified and refined metamodels may provide insights into the complex dynamic system before their transition to more sophisticated models that run on high-performance computing systems. The ultimate goal is to build a bridge between simulation and experiment, allowing model validation by comparing the simulated data to experimental data in microbiology.

scholarly journals QSAR-АНАЛІЗ БІБЛІОТЕК 4-ТІАЗОЛІДИНОН-СПОРІДНЕНИХ ГЕТЕРОЦИКЛІВ ДЛЯ ПРОГНОЗУВАННЯ ПРОТИТРИПАНОСОМНИХ ВЛАСТИВОСТЕЙ НОВИХ ПОХІДНИХ

2021 ◽  
pp. 39-46
Author(s):  
A. P. Kryshchyshyn-Dylevych
Keyword(s):  
Neural Networks ◽  
Random Forest ◽  
Trypanosoma Brucei ◽  
Trypanosoma Brucei Brucei ◽  
Random Forest Regression ◽  
Trypanosoma Brucei Gambiense ◽  
Chemical Database

Вступ. Похідні тіазолідинону та споріднених гетероциклів є джерелом нових протипаразитарних агентів, у тому числі молекул із протитрипаносомними властивостями. В актуальних наукових джерелах знайдено ряд досліджень про кількісний взаємозв’язок структура – протитрипаносомна активність, що включає різні підходи комп’ютерної хімії. Більшість досліджень належить до так званих мультитаргетних, коли до вибірки включають результати інших видів протипаразитарних активностей. Розробка нових QSAR-моделей похідних тіазолідинону з протитрипаносомними властивостями дозволить окреслити напрямки спрямованого дизайну нових протипаразитарних агентів на основі циклів тіазолу та тіазолідинону. Мета дослідження – встановити кількісний взаємозв’язок структура – протитрипаносомна активність у межах бібліотек тіазолідинонів та споріднених гетероциклів. Методи дослідження. Побудову математичних моделей на основі QSAR-аналізу здійснювали за допомогою онлайн-платформи Online Chemical Database. Результати й обговорення. Аналіз кількісного взаємозв’язку структура – протитрипаносомна активність проводили із застосуванням математичної моделі асоціативних нейронних мереж (ASNN: Associative Neural Networks) та методу регресії Random Forest (RFR: Random Forest regression) на основі вибірок, що включали похідні ізотіокумарин-3-карбонових кислот, тіопіранотіазолів і 4-тіазолідинон-імідазотіадіазолів із встановленою трипаноцидною активністю щодо Trypanosoma brucei brucei та Trypanosoma brucei gambiense. Кращу прогнозувальну здатність для групи ізотіокумарин-3-карбонових кислот і тіопірано[2,3-d][1,3]тіазол-2-онів обчислено за допомогою алгоритму Random Forest. Модель, обчислена на основі алгоритму Random Forest для групи імідазотіадіазолів, володіє найвищою прогнозувальною здатністю зі значенням R2=0,96. Висновок. На основі методів асоціативних нейронних мереж та регресії Random Forest розроблено прогностичні моделі для прогнозування протипаразитарної активності диверсифікованих похідних ­4-тіазолідинонів і подальшого фокусування напрямків оптимізації нових біологічно активних молекул із трипаноцидними властивостями.

Crop Quality Prediction Using Ml And Neural Networks

2021 ◽  
Vol 10 (02) ◽  
pp. 07-11
Author(s):  
Kanakaveti Narasimha Dheeraj ◽  
Goutham. R. J ◽  
Arthi. L
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Neural Networks ◽  
Random Forest ◽  
Machine Learning Techniques ◽  
Quality Prediction ◽  
Random Forest Regression ◽  
Power Efficient ◽  
Learning Techniques ◽  
Better Than

Agriculture is said to be the backbone of the economy. Farmers toil hard with different kinds of crops to make good and healthy food for the country. There are more existing systems but uses outdated machine-learning techniques based on RNN( Recurrent neural network) which makes the process slower and more time-consuming. Here We are proposing a new CNN(Convolutional neural network ) based system which is fast and gives accurate results within seconds. CNN is power-efficient and is more suitable for real-time implementation. In this project, we use CNN algorithms which is very much better than the RNN algorithms used in the existing system.More parameters will be taken for the consideration of prediction in the proposed system. And we use Random Forest Regression, Multiple Linear Regression

Knee Muscle Force Estimating Model Using Machine Learning Approach

2020 ◽  
Author(s):  
Anurag Sohane ◽  
Ravinder Agarwal
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Muscle Force ◽  
Vastus Lateralis ◽  
Input Parameter ◽  
Research Work ◽  
Cost Effective ◽  
Coefficient Of Determination ◽  
Muscle Forces ◽  
Knee Muscle

Abstract Various simulation type tools and conventional algorithms are being used to determine knee muscle forces of human during dynamic movement. These all may be good for clinical uses, but have some drawbacks, such as higher computational times, muscle redundancy and less cost-effective solution. Recently, there has been an interest to develop supervised learning-based prediction model for the computationally demanding process. The present research work is used to develop a cost-effective and efficient machine learning (ML) based models to predict knee muscle force for clinical interventions for the given input parameter like height, mass and angle. A dataset of 500 human musculoskeletal, have been trained and tested using four different ML models to predict knee muscle force. This dataset has obtained from anybody modeling software using AnyPyTools, where human musculoskeletal has been utilized to perform squatting movement during inverse dynamic analysis. The result based on the datasets predicts that the random forest ML model outperforms than the other selected models: neural network, generalized linear model, decision tree in terms of mean square error (MSE), coefficient of determination (R2), and Correlation (r). The MSE of predicted vs actual muscle forces obtained from the random forest model for Biceps Femoris, Rectus Femoris, Vastus Medialis, Vastus Lateralis are 19.92, 9.06, 5.97, 5.46, Correlation are 0.94, 0.92, 0.92, 0.94 and R2 are 0.88, 0.84, 0.84 and 0.89 for the test dataset, respectively.

scholarly journals Sensuator: A Hybrid Sensor–Actuator Approach to Soft Robotic Proprioception Using Recurrent Neural Networks

Actuators ◽  
2021 ◽  
Vol 10 (2) ◽  
pp. 30
Author(s):  
Pornthep Preechayasomboon ◽  
Eric Rombokas
Keyword(s):  
Neural Networks ◽  
Recurrent Neural Networks ◽  
Linear Models ◽  
Open Loop ◽  
Proof Of Concept ◽  
State Estimator ◽  
Loop Control ◽  
Practical Applications ◽  
Soft Actuator ◽  
The Cost

Soft robotic actuators are now being used in practical applications; however, they are often limited to open-loop control that relies on the inherent compliance of the actuator. Achieving human-like manipulation and grasping with soft robotic actuators requires at least some form of sensing, which often comes at the cost of complex fabrication and purposefully built sensor structures. In this paper, we utilize the actuating fluid itself as a sensing medium to achieve high-fidelity proprioception in a soft actuator. As our sensors are somewhat unstructured, their readings are difficult to interpret using linear models. We therefore present a proof of concept of a method for deriving the pose of the soft actuator using recurrent neural networks. We present the experimental setup and our learned state estimator to show that our method is viable for achieving proprioception and is also robust to common sensor failures.

Sign in / Sign up

Export Citation Format

Share Document