Evolutionary algorithms for species distribution modelling: A review in the context of machine learning

Cheng

2019

Entropy

Understanding or estimating the co-evolution processes is critical in ecology, but very challenging. Traditional methods are difficult to deal with the complex processes of evolution and to predict their consequences on nature. In this paper, we use the deep-reinforcement learning algorithms to endow the organism with learning ability, and simulate their evolution process by using the Monte Carlo simulation algorithm in a large-scale ecosystem. The combination of the two algorithms allows organisms to use experiences to determine their behavior through interaction with that environment, and to pass on experience to their offspring. Our research showed that the predators' reinforcement learning ability contributed to the stability of the ecosystem and helped predators obtain a more reasonable behavior pattern of coexistence with its prey. The reinforcement learning effect of prey on its own population was not as good as that of predators and increased the risk of extinction of predators. The inconsistent learning periods and speed of prey and predators aggravated that risk. The co-evolution of the two species had resulted in fewer numbers of their populations due to their potentially antagonistic evolutionary networks. If the learnable predators and prey invade an ecosystem at the same time, prey had an advantage. Thus, the proposed model illustrates the influence of learning mechanism on a predator-prey ecosystem and demonstrates the feasibility of predicting the behavior evolution in a predator-prey ecosystem using AI approaches.

Section: Introductionmentioning

confidence: 99%

Deep-Reinforcement Learning-Based Co-Evolution in a Predator–Prey System

Cheng

2019

Entropy

Measurement and Control

“…They are easy to implement parallel 19 but need much more time. 20,21 Others methods like annealing need less computational time but they are prone to fall into the local optimum.…”

Section: Literature Reviewmentioning

confidence: 99%

A new automatic machine learning based hyperparameter optimization for workpiece quality prediction

Wen

Gao

2020

Workpiece quality prediction is very important in modern manufacturing industry. However, traditional machine learning methods are very sensitive to their hyperparameters, making the tuning of the machine learning methods essential to improve the prediction performance. Hyperparameter optimization (HPO) approaches are applied attempting to tune hyperparameters, such as grid search and random search. However, the hyperparameters space for workpiece quality prediction model is high dimension and it consists with continuous, combinational and conditional types of hyperparameters, which is difficult to be tuned. In this article, a new automatic machine learning based HPO, named adaptive Tree Pazen Estimator (ATPE), is proposed for workpiece quality prediction in high dimension. In the proposed method, it can iteratively search the best combination of hyperparameters in the automatic way. During the warm-up process for ATPE, it can adaptively adjust the hyperparameter interval to guide the search. The proposed ATPE is tested on sparse stack autoencoder based MNIST and XGBoost based WorkpieceQuality dataset, and the results show that ATPE provides the state-of-the-art performances in high-dimensional space and can search the hyperparameters in reasonable range by comparing with Tree Pazen Estimator, annealing, and random search, showing its potential in the field of workpiece quality prediction.

“…We just tuned model accuracy that was acceptable. In future study, machine learning algorithm should be applied in model calibration, for searching best parameter groups [67]. Lastly, the responses of grassland growth NPP to climate changes are the product of complicated interactions among environment factors, such as nitrogen deposition changes, human disturbance, and land use change [68,69].…”

Section: Uncertaintymentioning

confidence: 99%

Grassland Productivity Response to Climate Change in the Hulunbuir Steppes of China

Zhang

2019

Sustainability

As global climate change deeply affects terrestrial ecosystem carbon cycle, it is necessary to understand how grasslands respond to climate change. In this study, we examined the role of climate change on net primary productivity (NPP) from 1961 to 2010 in the Hulunbuir grasslands of China, using a calibrated process-based biogeochemistry model. The results indicated that: Temperature experienced a rise trend from 1961; summer and autumn precipitation showed a rise trend before the 1990s and decline trend after the 1990s. Winter and spring precipitation showed an ascending trend. Simulated NPP had a high inter-annual variability during the study period, ranging from 139 g Cm−2 to 348 g Cm−2. The annual mean NPP was significant and positive in correlation with the annual variation of precipitation, and the trend was first raised then fell with the turn point at the 1990s. Temperature had a 20–30 d lag in summer, but none in spring and autumn; precipitation had a 10–20 d lag in summer. The climate lag effect analysis confirmed that temperature had a positive effect on NPP in spring and a negative effect in summer.