Proceeding Paper Cover and Land Use Changes in the Dry Forest of Tumbes (Peru) Using Sentinel-2 and Google Earth Engine Data † Elgar Barboza 1,2 , Wilian Salazar 1 , David Gálvez-Paucar 3, Lamberto Valqui-Valqui 1 , David Saravia 1, Jhony Gonzales 3, Wiliam Aldana 3, Héctor V. Vásquez 1,2 and Carlos I. Arbizu 1,* 1 Dirección de Desarrollo Tecnológico Agrario, Instituto Nacional de Innovación Agraria (INIA), Av. La Molina, 1981, Lima 15024, Peru 2 Instituto de Investigación Para el Desarrollo Sustentable de Ceja de Selva (INDES-CES), Universidad Nacional Toribio Rodríguez de Mendoza de Amazonas, Chachapoyas 01001, Peru 3 Instituto de Investigación en Desarrollo Sostenible y Cambio Climático, Universidad Nacional de Frontera, Av. San Hilarión 101, Sullana 20103, Peru * Correspondence: carbizu@inia.gob.pe; Tel.: +51-979-371-014 † Presented at the 3rd International Electronic Conference on Forests—Exploring New Discoveries and New Directions in Forests, 15–31 October 2022; Available online: https://iecf2022.sciforum.net/. Abstract: Dry forests are home to large amounts of biodiversity, are providers of ecosystem services, and control the advance of deserts. However, globally, these ecosystems are being threatened by various factors such as climate change, deforestation, and land use and land cover (LULC). The objective of this study was to identify the dynamics of LULC changes and the factors associated with the transformations of the dry forest in the Tumbes region (Peru) using Google Earth Engine (GEE). For this, the annual collection of Sentinel 2 (S2) satellite images of 2017 and 2021 was analyzed. Six types of LULC were identified, namely urban area (AU), agricultural land (AL), land without or with little vegetation (LW), water body (WB), dense dry forest (DDF), and open dry forest (ODF). Citation: Barboza, E.; Salazar, W.; Subsequently, we applied the Random Forest (RF) method for the classification. LULC maps reported Gálvez-Paucar, D.; Valqui-Valqui, L.; accuracies greater than 89%. In turn, the rates of DDF and ODF between 2017 and 2021 remained Saravia, D.; Gonzales, J.; Aldana, W.; unchanged at around 82%. Likewise, the largest net change occurred in the areas of WB, AL, and Vásquez, H.V.; Arbizu, C.I. Cover UA, at 51, 22, and 21%, respectively. Meanwhile, forest cover reported a loss of 4% (165.09 km2) of and Land Use Changes in the Dry the total area in the analyzed period (2017–2021). The application of GEE allowed for an evaluation Forest of Tumbes (Peru) Using of the changes in forest cover and land use in the dry forest, and from this, it provided important Sentinel-2 and Google Earth Engine information for the sustainable management of this ecosystem. Data. Environ. Sci. Proc. 2022, 22, 2. https://doi.org/10.3390/ Keywords: forest remote sensing; Random Forest (RF); temporal series; biodiversity IECF2022-13095 Academic Editor: Giorgos Mallinis Published: 21 October 2022 1. Introduction Publisher’s Note: MDPI stays neutral The dry forest plays an important role in the provision of ecosystem services such as with regard to jurisdictional claims in the conservation of endemic flora and fauna species, medicinal plants, wood, firewood, published maps and institutional affil- and plant foods [1,2]. It is made up of deciduous vegetation, where most of the dominant iations. tree species eliminate approximately 75% of their foliage during the long dry period of the year [3,4]. These forests are also recognized as one of the most threatened ecosystems worldwide [4], as they are exposed to many threats such as deforestation, fragmentation, Copyright: © 2022 by the authors. overgrazing, forest fires, droughts, and LULC changes [5,6]. LULC changes exert negative Licensee MDPI, Basel, Switzerland. impacts on ecosystems affecting climate, soil, water, and air, which are generally induced This article is an open access article by the interaction of demographic, socioeconomic, political, and biophysical factors [7,8]. distributed under the terms and The LULC changes affect the loss of ecosystems that are transformed into pastures, crops, conditions of the Creative Commons or new areas of urban expansion. Additionally, they impact protected areas, reporting high Attribution (CC BY) license (https:// rates of forest loss [9]. creativecommons.org/licenses/by/ Currently, the application of remote sensing (RS) tools plays an important role in 4.0/). analyzing the dynamics of LULC changes through the analysis of medium-resolution Environ. Sci. Proc. 2022, 22, 2. https://doi.org/10.3390/IECF2022-13095 https://www.mdpi.com/journal/environsciproc Environ. Sci. Proc. 2022, 22, 2 2 of 6 or new areas of urban expansion. Additionally, they impact protected areas, reporting high rates of forest loss [9]. Environ. Sci. Proc. 2022, 22, 2 Currently, the application of remote sensing (RS) tools plays an important rol2e oifn6 analyzing the dynamics of LULC changes through the analysis of medium-resolution sat- ellite images such as Landsat and S2 [10]. In recent years, many studies have evaluated tshaete ilmlitpeaimct aogfe Ls UsuLcCh acshaLnagnedss aint adnidffeSr2e[n1t0 ]a.rIenasr eocfe ntht ey ewarosr,ldm a[1n1y,1s2tu].d Mieus lhtia-vteemevpaolruaal tSe2d itmheagime ppraoccteosfsiLnUg LhCas cbheaenng feuslliyn edxipffleorietendt oanre paslaotffotrhmesw suocrhld a[s1 G1,E12E] .[1M3]u thltri-otuemghp tohrea lapS2- pimlicaagteiopnr oofc essuspinegrvhisaesdb celeanssfifuilclaytieoxnp ulosiitnegd tohne pRlFa tmfoertmhosds,u wchithas reGliEaEbl[e1 r3e]stuhlrtos u[1g4h].t hIne Paeprpul,i cwateio fninodf tshuep edrevpisaertdmcelansts oifif cTautimonbeuss,i nwghtihceh RisF hmomethe otdo, dwivitehrsree leiacbolseyrsetesmulsts s[u1c4h]. aIns tPheer ud,rwy efofirnesdt tahnedd ae pdairvtemrseintyt ooff Teunmdebmesi,cw sphiecchieiss [h1o5m]. eHtoowdeivveerrs, etheeco fsoyrsetsetm iss esxupchosaesdt htoe Mdraynfyo rtehsrteaantsd aanddi vimerpsiatcytso fthenatd eamrei creslpaetecdie sto[ 1h5u].mHaonw aecvtievr,ittihees f[o1r6e]s. tFiosre xthpioss reedastoonM, athney othbrjeecattisvaen odf itmhips ascttusdtyh awt aasr etore elavtaelduatoteh tuhme cahnaancgteivsi tiine sL[U16L]C. Finor ththei sdrreya fsoorne,stth oef oTbujemctbivese (oPfetrhuis) ustsuindgy Sw2a dsatotae avnadlu tahtee GthEeEc hpalantgfeosrmin iLnU thLeC pinertihoed dfrroymfo 2re0s1t7o tfoT 2u0m21b.e s (Peru) using S2 data and the GEE platform in the period from 2017 to 2021. 22.. MMaatteerriiaallss aanndd MMeetthhooddss 22..11.. SSttuuddyy AArreeaa TThhee ddeeppaarrttmeenntt ooff TTuumbbeess hhaass aann aarreeaa ooff 44664466..6677 kkm22 aanndd iiss llooccaatteedd iinn tthhee nnoorrtthh ooff PPeerruu,, bbeettweeeenn tthhee eexxttrreemee ccoooorrddiinnaatteess ooff llaattiittuuddee 33◦°2233..004455′′ aanndd 44°◦1133..884411′′ SS aanndd lloonnggiittuuddee 8800°◦2255..662255′ ′aanndd 8800°◦66.6.60099′ ′WW ((FFigiguurree 11)). .TThhee ssttuuddyy aarreeaa iiss paarrtt off tthee drry fforreesstt eeccossysstteem and fforrmss tthe Tuumbbeessr reeggioionn, ,d disitsrtirbibuutetdedb ebtewtweeenenP ePreuruan adndE cEucaudaodro[r1 6[1].6I]t. iIst fios ufonudnidn ai n anlt iatultditeudraen rgaentghea tthgaote gsoferso mfro0mto 01 t6o0 106m00a mbo avbeosveea sleva elle,vweli,t hwaitmh eaa mneaannn uanalntueaml pteemraptuere- athtuarteo sthcialtla otessciblleattwese ebnet2w0eaennd 2206 a◦nCda n26d °aCn naunadl raaninfuaalll breatinwfeaelln b3e0t0wmeemn i3n00th me lmow inla nthdes laonwdla7n0d0sm amndi n70th0 emhmig hinla tnhdes h, irgehsplaencdtisv,e rleys[p1e7c]t.ively [17]. Fiigure 1.. Loccaattiion off tthe deparrttmentt off Tumbes iin Peru.. 22..22.. IImmaaggee AAccqquuiissiittiioonn aanndd PPrroocceessssiinngg TThhee ddaattaa wwaass rreepprreesseenntteedd bbyy SS22 iimmaaggeess ffrroomm 22001177 ttoo 22002211 ((FFiigguurree 22)),, wwiitthh aa ssppaattiiaall rreessoolluuttiioonn ooff 1100 mm.. IImmaaggee pprroocceessssiinnggw waassp peerfroformrmededi ninG GEEEE[1 [31]3.]T. oToim imprporvoevteh tehqeu qauliatylitoyf othf ethSe2 Sim2 aimgeasg, eths,e tmhee tmadeatatadaaptap laipedplaiefidlt aer ftihltaetr ctohnasti dcoenresdidcelroeudd ccloovuedr lceosvsetrh alens3s 0t%ha[n1 83,01%9] . [C18lo,1u9d]. aCnldoucdlo aundd schloauddo wshmadaoswki nmgaswkainsgt hweans ptheerfno rpmerefdortmherodu tghhrotuhgehC thloeu CdlSocuodreScaonrde Temporal Dark Outlier Mask (TDOM) algorithms using the Quality Assessment (QA60) band [20]. Subsequently, the vegetation indices were calculated, namely the Normalized Difference Vegetation Index (NDVI), the Normalized Difference Water Index (NDWI), the Enhanced Vegetation Index (EVI), and the Soil Adjusted Vegetation Index (SAVI), with the objective of having more variables for the supervised classification process. Finally, the Environ. Sci. Proc. 2022, 22, 2 3 of 6 and Temporal Dark Outlier Mask (TDOM) algorithms using the Quality Assessment Environ. Sci. Proc. 2022, 22, 2 (QA60) band [20]. Subsequently, the vegetation indices were calculated, namely the No3ro-f 6 malized Difference Vegetation Index (NDVI), the Normalized Difference Water Index (NDWI), the Enhanced Vegetation Index (EVI), and the Soil Adjusted Vegetation Index (SAVI), with the objective of having more variables for the supervised classification pro- mceisnsi.m Fiunmal,lym, tahxeim muinmim, aunmd, mmeadxiiamnuvmal, uaensdf omreedaicahn bvaanludesa nfodr tehaechv ebgaentda taionnd itnhdei vceesgewtae-re ctiaolcnu ilnadteicdesto wbeuriel dcaalcmulualtteid-b taon bdumildo saa imc ufoltri-ebaacnhdy meaors. aic for each year. FFiigguurree 22.. Meetthhooddoollooggiiccaall ffllooww aapppplliieedd ttoo aannaalylyzzee ththee LLUULLCC chchaannggese sinin thteh edrdyr yfofroersets otfo tfhteh TeuTmumbebse s rreeggiioonn ((PPeerruu)).. 2..3.. Classiffiication of Images and Maap ooff LLaanndd Ussee aanndd CCoovveerr CChhaannggee The training areas werre rreprreesseenntteedd bbyy ssixix tytyppeess oof fLLUULLCC, ,nnamameleyl:y u: rubrabna naraerae (aU(AU)A, ), agriiculltturall llaanndd( A(ALL),),l alnadndw withitohuotuot rowr iwthitlhit tleittvle gveetagteitoanti(oLnW ()L,Ww)a,t ewrabtoedr yb(oWdyB )(,WdeBn),s e dreynsfoe rdersyt (fDorDeFst) ,(aDnDdFo),p aendd orypefno rdesryt (fOorDeFst) ,(tOhDatFw), ethreati dweenrteifi ieddenintiftiheed fiine ltdhae nfdielsda taenlldit e ismataeglleitse. iSmuapgeersv. iSseudpecrlvaissseidfi ccalatisosnifiwcaatsiopne wrfaosr mperdfotrhmroeudg thrtohuegRhF thme oRdFe lm. oPdrieol.r Ptoriocrla tsos i- ficlcaastsiiofnic,a2ti0o,n00, 200t,r0a0i0n tinraginpionign ptsoiwntesr ewrearne draonmdloymgleyn geernaeteradteadn danddi vdiidveidepdr porpooprotirotinoanlalyllyb y tbyyp ety[p2e1 ][a2n1]d ayneda ryoefare voaf luevaatilouna.tiIotnw. aIts wneacse snseacreysstaorpye trofo premrfaorvmis uaa vl iasnually asnisaolyfstihse ocfa trhtoeg - rcaprthoyguraspinhgy huigsihn-gre hsioglhu-trioensoilmutaigoens iimnaAgrecsG iInS Av.rc1G0.I5S. Svu. 1b0se.5q. uSeunbtslye,qtuhenitnltye,n tshiety i,nltoesns,sigtyai,n , alonsds,a gnaniun,a al nradt eanonf uchala nragte ionf tchheanangael iynz ethdep aenraiolydz(e2d0 1p7e–r2io0d2 1()20[127,–2220]2w1)e [r1e2d,2e2te] rwmeirnee de. - termined. 2.4. Validation of the Results 2.4. VTahliedafitnioanl ocfl athses iRfiesdulmts aps were compared with reference data, such as Google Earth satellTithee ifminaagl ecrlyasasinfidedP mlanapetsS wcoepre ,coumsinpgareadc wonitfhu srieofneremnacetr dixa.taF, osurcth iass, G20o3ogrlaen Edaormthl y dsaistetrlilbitue tiemdavgaelriyd atnidon PplaonienttSscwopeer,e uussinegd afo croenafcuhsiotynp me,aatsrisxu. mFoinr gthaisp, r2e0c3i sriaondeormrolry odfis3-% wtriitbhuitneda cvoanlifiddaetinocne ipnotienrtvsa lwoefr9e6 u%s,ewd hfiocrh eaallcohw teydpec,a lacsusluamtininggt hae pgreenceisriaolnp reercriosrio onf (O3%A ), uwsietrhipnr eac ciosinofnid(eUnAce) ,inptreercvisailo onf 9o6f%th, ewphriocdh uaclleorw(PeAd )c,aalcnudlaKtianpgp tahein gdeenxer[2a2l p].recision (OA), user precision (UA), precision of the producer (PA), and Kappa index [22]. 3. Results 33..1 R. eLsUuLltCs Distribution and Accuracy Assessment 3.1. LTUhLeC2 D01is7traibnudti2o0n2 a1ndL UAcLcCurmacya pAsssfoesrsmtheentT umbes region are shown in Figure 3. It is obserTvheed 2th0a1t7t hanedD D20F2a1n LdUOLDCF mtyappess fhoard thael aTrguemrbseusr fraecgeioannd awree srehodwisntr iibnu Fteigdutrher o3u. gIth oisu t tohbe 2 2 ssetruvdedy athreaat ,thwei tDhDinFc arenads eOsDfrFo mtyp1e7s2 5h.a0d2 tao la1r8g2e2r. 9s9ukrfmacea annddf wroemre1 d8i4s4tr.9ib9uttoe1d8 t9h2r.o0u1gkhm- , r 2oeustp tehceti svteuldy.yT ahreeat,y wpeithof inAcUreaalsseos rfreopmor t1s72a5n.0in2c troe a1s8e22in.99it skmsu2r afancde ,frforomm 13864.47.199t oto4 188.0972.k0m1 fkomr 2t,h reesepveacltuivaetiloyn. Tyheea trys,pree osfp AecUti valesloy .reHpoowrtes vaenr ,inoctrheearsec lians is2t ess s,usrufcahcea, sfrAomL, 3l6o.c7a1t teod 4t8o.0t7h e nkomrt2h fwore tshtea nevdacluloasteiotno yweaatresr, breosdpieecst,idveeclyre. aHseodwbevye9r2, .o2t5hkerm clabsyse2s0, 2s1u.cIhn atsh eAsLa,m loecawteady, ttoh e LthWe naonrdthWwBestty apneds cslhooswe teod wsiamteirl abrosdpieast,i adlepcraettaesrends ,brye 9p2o.r2t5i nkgma2 breyd 2u0c2t1io. Inni tnhteh seaimr seu wrfaayc,e s othf e1 .L2W4 a anndd0 .W11B% t,yrpeessp eschtoivweelyd, saicmcoilradri nspgattoiatlh peaytetearrnsso, freepvaolrutiantgio an .reOdnutchtieonot ihne rthheairn dsu, rth- e afaccceusr aocfy 1o.2f4t haendL U0.L11C%m, arepsspfeocrti2v0e1ly7, aancdco2r0d2in1gr etpo otrhtee dyeOaArs voaf leuveaslugaretiaotner. Othna nth9e2 o%th, jeurs t ahsanUdA, tahned acPcAurwaceyre ogf rtehaet eLrUtLhCan m7a0pasn fdor7 210%1,7r aenspde 2c0ti2v1e rlye.pTorhteedK OapAp avainludeesx garlesaotesrh tohwane d values above 89%. Environ. Sci. Proc. 2022, 22, 2 4 of 6 Environ. Sci. Proc. 2022, 22, 2 4 of 6 92%, just as UA and PA were greater than 70 and 71%, respectively. The Kappa index also Environ. Sci. Proc. 2022, 22, 2 9s2h%ow, juedst vaasl UueAs abnodv PeA 8 9w%e.r e greater than 70 and 71%, respectively. The Kappa index a4lsoof 6 showed values above 89%. Figure 3. LULC spatial distribution maps for the Tumbes region: (a) 2017 and (b) 2021. Figure 3. LULC spatial distribution maps for the Tumbes region: (a) 2017 and (b) 2021. Figure 3. LULC spatial distribution maps for the Tumbes region: (a) 2017 and (b) 2021. 33.2.2. .AAnnalaylysissi sofo fLLUULLCC CChhaannggese s 3.2. ATnThahleye saiansn aoalfy lLysUissi LsoCof feCeshstaitmnimgaeatset edd raratetes sfofor rththee 22001177––22002211 ppeeriroiodd rreeppoortrsts aa mmaarrkkeedd ddyynnaammicic fofor rLTLUhULeLC aC.n T.ahTlyehs ceish caohnfa genesgstie ms amitneadliyn rloayctceousc rcfrouerrd rt ehinde t2ihn0e1 ti7hn–ec2r0ien2ac1sr eepsae osrefi osUdoA fr e(Up4.Ao8r1t(%s4 .a)8, 1mD%Da)rF,k De(1dD. 3dF9y%(n1)a.,3 ma9ni%cd ) , fOoarDn LdFU (O0L.DC63.F %T(h)0.e. T6 c3hh%ias) ni.sg aTe shr emisuaislitn aolyfr teohsceuc urlterdroeufdct htiineo ntrh eiend iuAnccLtri o(e−an5s.ei9ns2 o%Af) LU, W(A−B (54 (..−98121.%92)),%, WD),D BanF(d −(1 B1.3S.9 (2%−%2).,)6 ,a7na%dn)d OraBDtSeFs( (.− 0L.26i.3k6%7e%w).)i Tsreha,i tset hsis.e a Lg irkreesauwtleits oetf , cthea nrgegrdeusa tcoetiscotcnuc hrinrae nAdg Lei ns(− o5Uc.9cAu2 %r(r5)e5,d W.3i6nB% U(−),A1 .W9(52B5% .3()4,6 a8%n.1)d7, %WBS)B, ( −a(42n8.d6.17 7A%%L) ) , r(a4at7ne.sd0.3 A%LLi)k. (eI4wn7 i.t0sue3r,% nt,)h .teIh neg trlueaarngte,eststht ecnhleatr ncggheeasstn ngoec ctwuchrarase ndrge epinrw eUsaesAnr te(p5d5r e.b3sy6e %nWt)e,B d,W bAByL W,( 4a8Bn.,1dA7 U%LA,),a noandf d5U 1A.2L7o, f (245171..60.2737,% ,a2)n.1 dI.6n 27 t0,u.a6rn6nd%, t2,h 0re.e6 sl6ap%regc,etrisevts epnlyect. tFcivhoearl nyigt.seF powraarist,s rFpeiapgrute,rseFe in4gt uesdrhe ob4wys shW othBwe, sActhLae,n acgnhedasn UpgreAos dpoufr co5ed1du. 2cb7ey,d 2L1bU.y6L7LC, Ua dnLudCr i2dn0ug.6 rti6hn%eg ,a trnheaeslpyaensicastl iypvseirlsyiop. deF.ro iCro odint.ss Cepqoaunrets,ne qFtliuyge,u n7rt3el%y 4, 7os3fh %tohweo sff ottrhees ftco shruaersnftgasecues rrpfearmcoedaruinecmeda iubnnye-d LcuUhnaLncChg aedndug, reainds g,d atishdde a iadnnthanlryothspirso gpeeonrgieocn dui.c sCeu os(naegs(eraiqgcurielctnutllrtyau,l r 7ala3ln%lad n oadfn tadhn edu froubraebnsa tna sruaeraef)a (c)1e(5 1r%5e%m). )aH. iHnoewodwe uveenvr-e,r , c4h4%a%n (g1(16e65d5.,0 .0a99s k kdmmid2)2 )oaonf fththreo etpototagtlae lanariercea ua lsoleos ts( tiatigst rsfiofcoruerlestuts trcacolov vleaern.r .d and urban area) (15%). However, 4% (165.09 km2) of the total area lost its forest cover. FFigiguurere 44. .MMapaps soof fththe echchanangge eanandd pperemrmaannenencec eoof fLLUULLCC ththa at tooccucurreredd bbeetwtweeenn 22001177 aanndd 22002211 inin ththee FTiTugumumrbebe 4ess. rMreegagipoiosnn .o .f the change and permanence of LULC that occurred between 2017 and 2021 in the Tumbes region. 4. Discussion The dry forest of the north coast of Peru is considered the most sensitive region to the El Niño phenomenon (ENP) [23], which mainly affects the populations settled in this ecosystem. Likewise, the vegetation is conditioned by climatic factors, such as precipitation and temperature since they have a marked effect on the regeneration and physiognomy of Environ. Sci. Proc. 2022, 22, 2 5 of 6 the vegetation cover [24]. However, ENP can also have some positive impacts, especially in rural communities where they favor some crops such as rice, the appearance of temporary grasslands for cattle, and the regeneration of dry forests [25]. The results of the main types of LULC in the Tumbes region reported an increase in forest cover of approximately 2% by 2021. However, in areas near UA and LW, foci of forest loss were shown. These changes could be related to the expansion of the agricultural frontier, firewood extraction, or deforestation [5,24]. Another important aspect is the decrease in the AL surface from 425.65 to 333.40 ha from 2017 to 2021. This reduction could be related to water availability since the ENP occurred in 2017, which increased the crop plots in the study area. 5. Conclusions In this study, we used 10-m multi-temporal S2 images to analyze LULC changes in the Tumbes region from 2017 to 2021, which were implemented on the GEE platform. The generated maps reported accuracies greater than 89%, which were evaluated with other available high-resolution images. Through the comparison of the LULC maps, it was reported that forest cover in recent years has lost 4% of the total area. In addition, the application of GEE made it possible to evaluate the LULC changes in the dry forest and, from this, provide important information for the sustainable management of this important ecosystem. Author Contributions: Conceptualization, E.B. and W.S.; methodology, E.B., W.S., D.G.-P., L.V.-V., D.S. and J.G.; validation, E.B., D.G.-P., J.G., W.A. and H.V.V.; formal analysis, E.B., W.S. and D.G.-P.; investigation, E.B., W.S. and C.I.A.; resources, J.G., H.V.V. and C.I.A.; data curation, E.B., W.S. and L.V.-V.; writing—original draft preparation, E.B., D.S. and C.I.A.; writing—review and editing, C.I.A.; visualization, E.B., W.A. and H.V.V.; supervision, W.S., J.G., H.V.V. and C.I.A.; project administration, J.G., H.V.V. and C.I.A.; funding acquisition, J.G., H.V.V. and C.I.A. All authors have read and agreed to the published version of the manuscript. Funding: This research was funded by PP068 “Reducción de la vulnerabilidad y atención de emer- gencias por desastres” of the Ministry of Agrarian Development and Irrigation (MIDAGRI) of the Peruvian Government, and Universidad Nacional de Frontera (UNF). Institutional Review Board Statement: Not applicable. Informed Consent Statement: Not applicable. Data Availability Statement: Not applicable. Acknowledgments: We thank Ivan Ucharima for image processing and “Centro Experimental La Molina” for providing field resources. In addition, we thank Eric Rodriguez, Maria Angélica Puyo, and Cristina Aybar for supporting the logistic activities in our laboratory. Finally, the authors thank the Bioinformatics High-Performance Computing server of Universidad Nacional Agraria la Molina for providing resources for data analysis. Conflicts of Interest: The authors declare no conflict of interest. References 1. Padilla, N.A.; Alvarado, J.; Granda, J. Bienes y Servicios Ecosistémicos de Los Bosques Secos de La Provincia de Loja. Bosques Latid. Cero 2018, 8, 2. Available online: https://revistas.unl.edu.ec/index.php/bosques/article/view/499 (accessed on 30 April 2022). 2. Mercado, W.; Rimac, D. Comercialización de miel de abeja del bosque seco, distrito de Motupe, Lambayeque, Perú. Nat. Econ. 2019, 4, 24–37. [CrossRef] 3. MINAM. Mapa Nacional de Cobertura Vegetal; MINAM: Lima, Perú, 2015. Available online: https://www.gob.pe/institucion/ minam/informes-publicaciones/2674-mapa-nacional-de-cobertura-vegetal-memoria-descriptiva (accessed on 10 August 2022). 4. Espinosa, C.I.; de la Cruz, M.; Luzuriaga, A.L.; Escudero, A. Bosques Tropicales Secos de La Región Pacífico Ecuatorial: Diversidad, Estructura, Funcionamiento e Implicaciones Para La Conservación. Ecosistemas 2012, 21, 167–179. 5. Whaley, O.Q.; Beresford-Jones, D.G.; Milliken, W.; Orellana, A.; Smyk, A.; Leguía, J. An ecosystem approach to restoration and sustainable management of dry forest in southern Peru. Kew Bull. 2010, 65, 613–641. [CrossRef] 6. Mantilla, P.G.; Neri, L. El ecoturismo como alternativa sostenible para proteger el bosque seco tropical peruano: El caso de Proyecto Hualtaco, Tumbes. Pasos. Rev. Turismo Patrim. Cult. 2015, 13, 1437–1449. [CrossRef] Environ. Sci. Proc. 2022, 22, 2 6 of 6 7. Negese, A. Impacts of Land Use and Land Cover Change on Soil Erosion and Hydrological Responses in Ethiopia. Appl. Environ. Soil Sci. 2021, 2021, 1–10. [CrossRef] 8. Birhanu, A.; Masih, I.; van der Zaag, P.; Nyssen, J.; Cai, X. Impacts of land use and land cover changes on hydrology of the Gumara catchment, Ethiopia. Phys. Chem. Earth Parts A/B/C 2019, 112, 165–174. [CrossRef] 9. Scullion, J.J.; Vogt, K.A.; Sienkiewicz, A.; Gmur, S.; Trujillo, C. Assessing the influence of land-cover change and conflicting land-use authorizations on ecosystem conversion on the forest frontier of Madre de Dios, Peru. Biol. Conserv. 2014, 171, 247–258. [CrossRef] 10. Khan, M.S.; Ullah, S.; Chen, L. Comparison on Land-Use/Land-Cover Indices in Explaining Land Surface Temperature Variations in the City of Beijing, China. Land 2021, 10, 1018. [CrossRef] 11. Kamwi, J.M.; Mbidzo, M. Impact of land use and land cover changes on landscape structure in the dry lands of Southern Africa: A case of the Zambezi Region, Namibia. GeoJournal 2020, 87, 87–98. [CrossRef] 12. Briceñojas, N.B.R.; Castillo, E.B.; Quintana, J.L.M.; Cruz, S.M.O.; López, R.S. Deforestatcioón ien the Peruvilan Amazonía peruana: Iíndexices de cambiofs Lande covber/Lturand y uso del (suelC/LU) Changeso basado ed on SIGIS. Bol. Asoc. Geogr. Esp. 2019, 81, 1–34. [CrossRef] 13. Gorelick, N.; Hancher, M.; Dixon, M.; Ilyushchenko, S.; Thau, D.; Moore, R. Google Earth Engine: Planetary-scale geospatial analysis for everyone. Remote Sens. Environ. 2017, 202, 18–27. [CrossRef] 14. Wang, J.; Qiu, L.; Wang, Z.; Huang, X.; Shan, J.; Li, M. Study on remote sensing feature selection of green manure crop Astragalus sinicus based on multitemporal Sentinel-2 imagery. In Proceedings of the 2021 9th International Conference on Agro-Geoinformatics (Agro-Geoinformatics), Shenzhen, China, 26–29 July 2021; pp. 1–5. 15. Marris, E. Conservation: Biodiversity as a bonus prize. Nature 2010, 468, 895. [CrossRef] 16. Ortiz, J.C.; Espinosa, C.I.; Dahik, C.Q.; Mendoza, Z.A.; Ortiz, E.C.; Gusmán, E.; Weber, M.; Hildebrandt, P. Influence of Anthropogenic Factors on the Diversity and Structure of a Dry Forest in the Central Part of the Tumbesian Region (Ecuador–Perú). Forests 2019, 10, 31. [CrossRef] 17. Aguirre, Z.; Kvist, L. Floristic Composition and Conservation Status of the Dry Forests in Ecuador. Lyonia 2005, 8, 41–67. 18. Arekhi, M.; Goksel, C.; Sanli, F.B.; Senel, G. Comparative Evaluation of the Spectral and Spatial Consistency of Sentinel-2 and Landsat-8 OLI Data for Igneada Longos Forest. ISPRS Int. J. Geo-Inf. 2019, 8, 56. [CrossRef] 19. Parente, L.; Ferreira, L. Assessing the Spatial and Occupation Dynamics of the Brazilian Pasturelands Based on the Automated Classification of MODIS Images from 2000 to 2016. Remote Sens. 2018, 10, 606. [CrossRef] 20. Samsammurphy. Cloud Masking with Sentinel 2. 2017. Available online: https://github.com/samsammurphy/cloud-masking- sentinel2/blob/master/cloud-masking-sentinel2.ipynb (accessed on 23 April 2020). 21. Hailemariam, S.N.; Soromessa, T.; Teketay, D. Land Use and Land Cover Change in the Bale Mountain Eco-Region of Ethiopia during 1985 to 2015. Land 2016, 5, 41. [CrossRef] 22. Chuvieco, E. Fundamentals of Satellite Remote Sensing. An Enviromental Approach, 2nd ed.; CRC Press, Taylor & Francis Group: New York, NY, USA, 2016; ISBN 978-1-4987-2807-2. 23. Rodríguez, R.; Mabres, A.; Luckman, B.; Evans, M.; Masiokas, M.; Ektvedt, T.M. “El Niño” events recorded in dry-forest species of the lowlands of northwest Peru. Dendrochronologia 2005, 22, 181–186. [CrossRef] 24. Zorogastúa, P.; Quiroz Guerra, R.; Garatuza Payán, J. Evaluación de Cambios En La Cobertura y Uso de La Tierra Con Imágenes de Satélite En Piura—Perú. Ecol. Appl. 2011, 10, 13–22. [CrossRef] 25. Pécastaing, N.; Chávez, C. The impact of El Niño phenomenon on dry forest-dependent communities’ welfare in the northern coast of Peru. Ecol. Econ. 2020, 178, 106820. [CrossRef]