Algal　bloom,　a　water　pollution　caused　by　marine　algae,　may　threaten　the　development　of　fisheries　due　to　some　toxic　algal　species.　Rapid　and　accurate　identification　of　red　tide　algal　species　and　their　cell　concentrations　is　important　for　pollution　control　and　management.　Traditional　detection　methods　such　as　microscope　and　gene　sequencing　have　low　timeliness,　remote　sensing　is　susceptible　to　environmental　interference　resulting　in　low　accuracy,　and　fluorescence　spectroscopy　is　too　expensive　for　widespread　use.　Hyperspectral　imaging　(HSI)　technology　provides　a　rapid　and　non-destructive　method　for　detecting　red　tide　algae　species.　In　this　study,　a　HSI　detection　system　was　built　to　establish　a　large　amount　of　hyperspectral　sample　libraries　constituted　of　dinophyta　(Amphidinium　carterae),　bacillariophyta　(Skeletonema　costatumand　Phaeodactylum　tricornutum)　and　raphidophyceae　(Heterosigma　akashiwo).　Two　classification　methods　and　three　regression　methods　were　used　to　construct　models　for　algal　species　identification　and　cell　concentration　measurement,　respectively,　and　the　effects　of　seven　spectral　pretreatment　methods　(Autoscaling,　Normalization,　Multiplicative　Scatter　Correction,　Standard　Normalized　Variate,　Savitzky-Golay　Smoothing,　First　Derivative　Based　on　Savitzky-Golay,　and　Second　Derivative　Based　on　Savitzky-Golay)　and　two　band　extraction　methods　(Genetic　Algorithms　and　Successive　Projections　Algorithm)　on　the　accuracy　of　modelling　were　investigated.　The　results　showed　that　the　Second　Derivative　Based　on　Savitzky-Golay　(SG+2(nd))　pretreatment　method　can　improve　the　accuracy　of　band　extraction　and　modelling,　and　that　the　feature　bands　selected　by　the　genetic　algorithm　(GA)　are　more　representative　and　effective.　The　feature　bands　(644.7,　547.8,　562.6,　829.4,　832　nm)　extracted　SG+2(nd)-GA　correspond　to　the　absorption　spectral　bands　of　specific　pigments　in　the　selected　algae,　combined　with　Support　Vector　Machine　(SVM)　or　Back　Propagation　Neural　Network　(BPNN)　modellingrealized　the　effective　identification　of　dinophyta,　bacillariophyta　and　raphidophyceae　using　HSI　technology.　Compared　to　Multiple　Linear　Regression　(MLR)　and　Partial　Least　Squares　(PLS)　algorithms,　Support　Vector　Regression　(SVR)　modelling　achieved　higher　accuracy　incell　concentration　measurements.　The　coefficients　of　determination　(R-2)　of　the　four　algal　SG+2(nd)-GA-SVR　cellconcentrations　prediction　models　were　all　greater　than　0.98.　Among　them,　the　predicted　concentrations　of　A.　carterae　e　and　S.　costatumranged　from　1.05x10(3)similar　to　1.05x10(4)　and　1.13x10(4)similar　to　2.38x10(5)　cells　center　dot　mL(-1),　with　the　lowest　measured　concentrations　reaching　the　benchmark　concentrations　for　this　algae　species　in　the　event　of　red　tide.　The　predicted　concentrations　of　P.　tricornutum　ranged　from　1.06x10(5)similar　to　4.36x10(6)　cells　center　dot　mL(-1),　with　the　lowest　measured　concentrations　being　lower　than　those　of　existing　spectroscopic　techniques.　This　study　provides　a　new　method　for　rapid,　accurate,　non-destructive　algal　blooms　detection.