Short-term Lake Erie algal bloom prediction by classification and regression models

Ai, Haiping; Zhang, Kai; Sun, Jiachun; Zhang, Huichun

doi:10.1016/j.watres.2023.119710

Cited by 24 publications

(13 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As the model performance shown in Table S1, except for convolutional neural network (CNN) and multilinear regression (MLR), all five tree-based ML regression models achieved comparable performance on the test set for P measurement. In this study, we chose to use RF as it can evaluate the input feature importance by the permutation approach ( Ai et al, 2023 ), which can help evaluate the feature importance below. As for the permutation approach, it calculates the feature importance by shuffling the order an input feature values and comparing the model performance before and after the shuffling ( Jones and Linder, 2015 ).…”

Section: Resultsmentioning

confidence: 99%

“…Apart from wastewater discharge, agriculture and animal husbandry are two main nutrient sources leading to eutrophication ( Sala and Mujeriego, 2001 ). In recent decades, Lake Erie has been plagued by harmful algal blooms, with soluble reactive phosphorus, primarily originating from non-point agricultural runoffs, identified as one of the key driving factors ( Ai et al, 2023 ; Ho and Michalak, 2017 ). Effective P monitoring and control are critical for mitigating eutrophication and harmful algal blooms.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Efficient smartphone-based measurement of phosphorus in water

Ai,

Zhang,

Zhang

2024

Water Research X

Self Cite

View full text Add to dashboard Cite

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Efficient smartphone-based measurement of phosphorus in water

Ai,

Zhang,

Zhang

2024

Water Research X

Self Cite

View full text Add to dashboard Cite

“… 100 RNNs enable the classification and characterization of temporal signals, while LSTMs are capable of learning long-term dependencies, especially in temporal information. Ai et al 101 built classification and regression models for short-term prediction of algal blooms in the Lake Erie area. They compiled a large data set consisting of the chlorophyll a index and a combination of riverine (the Maumee and Detroit Rivers) and meteorological features and used it to train ML-based classification and regression models for 10 day scale bloom predictions.…”

Section: Machine Learning Methods Applied To Habsmentioning

confidence: 99%

Toward a Predictive Understanding of Cyanobacterial Harmful Algal Blooms through AI Integration of Physical, Chemical, and Biological Data

Marrone,

Banerjee,

Talapatra

et al. 2023

ACS EST Water

View full text Add to dashboard Cite

Freshwater cyanobacterial harmful algal blooms (cyanoHABs) are a worldwide problem resulting in substantial economic losses, due to harm to drinking water supplies, commercial fishing, wildlife, property values, recreation, and tourism. Moreover, toxins produced from some cyanoHABs threaten human and animal health. Climate warming can affect the distribution of cyanoHABs, where rising temperatures facilitate more intense blooms and a greater distribution of cyanoHABs in inland freshwater. Nutrient runoff from adjacent watersheds is also a major driver of cyanoHAB formation. While some of the physicochemical factors behind cyanoHAB dynamics are known, there are still major gaps in our understanding of the conditions that trigger and sustain cyanoHABs over time. In this perspective, we suggest that sufficient data sets, as well as machine learning (ML) and artificial intelligence (AI) tools, are available to build a comprehensive model of cyanoHAB dynamics based on integrated environmental/climate, nutrient/water chemistry, and cyanoHAB microbiome and 'omics data to identify key factors contributing to HAB formation, intensity, and toxicity. By taking a holistic approach to the analysis of all available data, including the rapidly growing number of biological data sets, we can provide the foundational knowledge needed to address the increasing threat of cyanoHABs to the security of our water resources.

show abstract

“…Unveiling this nexus provides a crucial link between soil dynamics and the larger ecological context, particularly in relation to Lake Erie. The amalgamation of heightened nitrogen concentrations diminished retention capacity due to lower organic carbon, and the potential for nitrogen loss through volatilization points to a pathway through which the elevated nitrogen in the Maumee River watershed could impact Lake Erie's ecosystem Ai et al (2023). Relating the soil data to hydrologic pathways could help quantify nitrogen fluxes from vulnerable fields into Lake Erie.…”

Section: • Soil Chemical Propertiesmentioning

confidence: 99%

“…Ohio was selected as a baseline state and region of interest for this analysis given its significance in the Center for Advancing Sustainable and Distributed Fertilizer Production (CASFER), a National Science Foundation (NSF) Engineering Research Center (ERC) Botte et al (2023); Ai et al (2023). This state has major importance and serves as a baseline location where CASFER technologies will be implemented and validated for creating a nitrogen-circular economy.…”

Section: Introductionmentioning

confidence: 99%

Integrating Multiscale Geospatial Analysis for Monitoring Crop Growth, Nutrient Distribution, and Hydrological Dynamics in Large-Scale Agricultural Systems

Akanbi,

Bhuvanagiri,

Barcelos

et al. 2024

J geovis spat anal

View full text Add to dashboard Cite

Monitoring crop growth, soil conditions, and hydrological dynamics are imperative for sustainable agriculture and reduced environmental impacts. This interdisciplinary study integrates remote sensing, digital soil mapping, and hydrological data to elucidate intricate connections between these factors in the state of Ohio, USA. Advanced spatiotemporal analysis techniques were applied to key datasets, including the MODIS sensor satellite imagery, USDA crop data, soil datasets, Aster GDEM, and USGS stream gauge measurements. Vegetation indices derived from MODIS characterized crop-specific phenology and productivity patterns. Exploratory spatial data analysis show relationships of vegetation dynamics and soil properties, uncovering links between plant vigor, edaphic fertility, and nutrient distributions. Correlation analysis quantified these relationships and their seasonal evolution. Examination of stream gauge data revealed insights into spatiotemporal relationships of nutrient pollution and stream discharge. By synthesizing diverse geospatial data through cutting-edge data analytics, this work illuminated complex interactions between crop health, soil nutrients, and water quality in Ohio. The methodology and findings provide actionable perspectives to inform sustainable agricultural management and environmental policy. This study demonstrates the significant potential of open geospatial resources when integrated using a robust spatiotemporal framework. Integrating additional measurements and high-resolution data sources through advanced analytics and interactive visualizations could strengthen these insights.

show abstract

Short-term Lake Erie algal bloom prediction by classification and regression models

Cited by 24 publications

References 61 publications

Efficient smartphone-based measurement of phosphorus in water

Efficient smartphone-based measurement of phosphorus in water

Toward a Predictive Understanding of Cyanobacterial Harmful Algal Blooms through AI Integration of Physical, Chemical, and Biological Data

Integrating Multiscale Geospatial Analysis for Monitoring Crop Growth, Nutrient Distribution, and Hydrological Dynamics in Large-Scale Agricultural Systems

Contact Info

Product

Resources

About